Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Olivier D. FaugerasSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works400 from public data
- 3,072
- Microsoft Kinect Sensor and Its Effect2,583
While the Kinect sensor incorporates several advanced sensing hardware, this article focuses on the vision aspect of the sensor and its impact beyond the gaming industry.
- Deeplysupervised nets2,565
The proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent, and extends techniques from stochastic gradient methods to analyze the algorithm.
- Iterative point matching for registration of free-form curves and surfaces2,557
A heuristic method has been developed for registering two sets of 3-D curves obtained by using an edge-based stereo system, or two dense3-D maps obtained by use a correlation-based stereoscopic system, and it is efficient and robust, and yields an accurate motion estimate.
- Iterative point matching for registration of free-form curves2,557
A heuristic method has been developed for registering two sets of 3-D curves obtained by using an edge-based stereo system, or two dense3-D maps obtained by use a correlation-based stereoscopic system, and it is efficient and robust, and yields an accurate motion estimate.
- A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry1,662
A robust approach to image matching by exploiting the only available geometric constraint, namely, the epipolar constraint, is proposed and a new strategy for updating matches is developed, which only selects those matches having both high matching support and low matching ambiguity.
- 1,488
- Untitled1,109
A complete review of the current techniques for estimating the fundamental matrix and its uncertainty is provided, and a well-founded measure is proposed to compare these techniques.
- Parameter estimation techniques: a tutorial with application to conic fitting1,102
This tutorial presents what is probably the most commonly used techniques for parameter estimation, including linear least-squares (pseudo-inverse and eigen analysis); orthogonal least- Squares; gradient-weighted least-Squares; bias-corrected renormalization; Kalman filtering; and robust techniques (clustering, regression diagnostics, M-estimators, least median of squares).
- Training deep networks for facial expression recognition with crowd-sourced label distribution907
This paper shows how to learn a deep convolutional neural network (DCNN) from noisy labels, using facial expression recognition as an example, and compares four different approaches to utilizing the multiple labels.
- 746
- 682
- 680
- A Survey of Recent Advances in Face Detection658
This technical report surveys the recent advances in face detection for the past decade and surveys the various techniques according to how they extract features and what learning algorithms are adopted.
- Epipolar Geometry in Stereo, Motion and Object Recognition: A Unified Approach558
Redefining Stereo, Motion and Object Recognition via Ep bipolar Geometry via Epipolar Geometry, and Multiple Rigid Motions: Correspondence and Segmentation is redefined.
- Epipolar Geometry in Stereo, Motion and Object Recognition558
Redefining Stereo, Motion and Object Recognition via Ep bipolar Geometry via Epipolar Geometry, and Multiple Rigid Motions: Correspondence and Segmentation is redefined.
- A survey on face detection in the wild: Past, present and future489
The recent advances in real-world face detection techniques are surveyed, beginning with the seminal Viola-Jones face detector methodology and are roughly categorized into two general schemes: rigid templates, learned mainly via boosting based methods or by the application of deep neural networks, and deformable models that describe the face by its parts.
- Real time correlation-based stereo: algorithm, implementations and applications483
The algorithm that has been described is not the most sophisticated available but it has made it robust and reliable thanks to a number of improvements and has shown that real time stereo is possible today at low-cost and can be applied in real applications.
- Robust hand gesture recognition based on finger-earth mover's distance with a commodity depth camera455
A novel distance metric for hand dissimilarity measure, called Finger-Earth Mover's Distance (FEMD), which only matches fingers while not the whole hand shape, can better distinguish hand gestures of slight differences.
- 444
- Robust hand gesture recognition with kinect sensor323
This work presents a hand gesture recognition system with Kinect sensor, which operates robustly in uncontrolled environments and is insensitive to hand variations and distortions, and applies a novel shape distance metric called Finger-Earth Mover's Distance (FEMD) forHand gesture recognition.
- Expressive expression mapping with ratio images260
This paper captures the illumination change of one person's expression in what they call an expression ratio image (ERI), and together with geometric warping, they map an ERI to any other person's face image to generate more expressive facial expressions.
- Distributed meetings258
A system that provides speaker clustering, spatial indexing, and time compression to provide a rich experience for people who miss a meeting and want to watch it afterward and a user study evaluation of the system is described.
- Dimension Reduction With Extreme Learning Machine248
This paper introduces a dimension reduction framework which to some extend represents data as parts, has fast learning speed, and learns the between-class scatter subspace, and experimental results show the efficacy of linear and non-linear ELM-AE and SELM- AE in terms of discriminative capability, sparsity, training time, and normalized mean square error.
- 243
- 233
- 218
- 209
- Curriculum-guided Hindsight Experience Replay192
This paper proposes to adaptively select the failed experiences for replay according to the proximity to the true goals and the curiosity of exploration over diverse pseudo goals, and adopts a human-like learning strategy that enforces more curiosity in earlier stages and changes to larger goal-proximity later.
- 188
- FEATURE-BASED FACIAL EXPRESSION RECOGNITION: SENSITIVITY ANALYSIS AND EXPERIMENTS WITH A MULTILAYER PERCEPTRON181
Experiments show that facial expression recognition is mainly a low frequency process, and a spatial resolution of 64 pixels × 64 pixels is probably enough to represent the space of facial expressions.
- 3D Deformable Face Tracking with a Commodity Depth Camera178
A regularized maximum likelihood deformable model fitting (DMF) algorithm is developed, with special emphasis on handling the noisy input depth data, that can accommodate sensor noise represented by an arbitrary covariance matrix.
- Rapid modeling of animated faces from video173
A system that constructs textured 3D face models from videos with minimal user interaction and the goal is to allow an untrained user with a PC and an ordinary camera to create and instantly animate his/her face model in no more than a few minutes.
- Characterizing the Uncertainty of the Fundamental Matrix158
Two different methods to compute the fundamental matrix and its uncertainty at the same time are given and the definition of the epipolar band for stereo matching, projective reconstruction, and self-calibration is provided.
- 155
- Super-resolution wearable electrotactile rendering system154
A wearable electrotactile rendering system that elicits tactile stimuli with both high spatial resolution (76 dots/cm2) and rapid refresh rates (4 kHz) because of a previously unexplored current-steering super-resolution stimulation technique.
- 154
- 151
- Touch IoT enabled by wireless self-sensing and haptic-reproducing electronic skin141
A wireless self-sensing and haptic-reproducing electronic skin (e-skin) to realize noncontact touch communications and presents huge potentials in remote touch video, medical care/assistance, education, and many other applications.
- 141
- Visual panel: virtual mouse, keyboard and 3D controller with an ordinary piece of paper140
By detecting the clicking and dragging actions, the system can fulfill many tasks such as controlling a remote large display, and simulating a physical keyboard, as well as providing 3D information, serving as a virtual joystick, to control 3D virtual objects.
- Large-Scale Integrated Flexible Tactile Sensor Array for Sensitive Smart Robotic Touch139
This work demonstrated a 64 × 64 flexible tactile sensor array with a record-high spatial resolution of 0.9 mm by integrating a high-performance piezoresistive film (PRF) with a large-area active matrix of carbon nanotube thin-film transistors and hardware-implemented a smart tactile system.
- 134
- 131
- 126
- Three-dimensional motion computation and object segmentation in a long sequence of stereo frames126
The motion computation problem is formulated as a tracking problem in order to apply the extended Kalman filter and the tracking is performed in a prediction-matching-update loop in which multiple matches can be handled.
- 120
- 118
- Estimating motion and structure from correspondences of line segments between two perspective images118
- 116
- 113
- Simultaneous 2D images and 3D geometric model registration for texture mapping utilizing reflectance attribute106
This paper proposes the new simultaneous registration technique of several images and geometric model based on 2D-3D edge correspondence and the epipolar constraint between images.
- 105
- 104
- Lifelike agility and play in quadrupedal robots using reinforcement learning and generative pre-trained models103
A general learning framework for reusing pre-trained knowledge across different perception and task levels is proposed for reusing pre-trained knowledge across different perception and task levels in quadrupedal robots.
- Eye gaze tracking using an RGBD camera: a comparison with a RGB solution99
A non-infrared based approach to track one's eye gaze with an RGBD camera (in this case, Kinect) that adopts a personalized 3D face model constructed off-line and finds that the use of depth information directly from Kinect achieves more accurate tracking.
- Estimating motion and structure from correspondences of line segments between two perspective images93
- 3D Dynamic Scene Analysis: A Stereo Based Approach93
This book describes several approaches to the analysis of moving scenes using information from a stereovision system and shows that motion estimation can be further improved by the explicit modeling of uncertainty in geometric objects.
- 91
- Intelligent Recognition Using Ultralight Multifunctional Nano-Layered Carbon Aerogel Sensors with Human-Like Tactile Perception90
A new form of ultralight multifunctional tactile nano-layered carbon aerogel sensor that provides pressure, temperature, material recognition and 3D location capabilities, which is combined with multimodal supervised learning algorithms for object recognition.
- 87
- Robust and Rapid Generation of Animated Faces from Video Images: A Model-Based Modeling Approach87
An easy-to-use and cost-effective system to construct textured 3D animated face models from videos with minimal user interaction, which makes full use of generic knowledge of faces in head motion determination, head tracking, model fitting, and multiple-view bundle adjustment.
- High-Fidelity 3D Digital Human Head Creation from RGB-D Selfies85
A new facial geometry modeling and reflectance synthesis procedure that significantly improves the state of the art and combines parametric fitting and Convolutional Neural Networks to synthesize high-resolution albedo/normal maps with realistic hair/pore/wrinkle details.
- Joint Hand-Object 3D Reconstruction From a Single Image With Cross-Branch Feature Fusion84
This work proposes to consider hand and object jointly in feature space and explore the reciprocity of the two branches in cross-branch feature fusion architectures with MLP or LSTM units, and significantly outperforms existing approaches in terms of the reconstruction accuracy of objects.
- 84
- 83
- 82
- 81
- 80
- Whiteboard scanning and image enhancement80
This paper describes a system that automatically locates the boundary of a whiteboard, crops out the whiteboard region, rectifies it into a rectangle, and corrects the color to make the white board completely white.
- Miniaturization of mechanical actuators in skin-integrated electronics for haptic interfaces79
A class of materials and mechanical designs for the miniaturization of mechanical actuators and strategies for their integration into thin, soft e-skin for haptic interfaces that conformally fit onto various parts of the human body to afford programmable tactile enhancement and Braille recognition with an accuracy rate over 85%.
- Real-time high-resolution sparse voxelization with application to image-based modeling79
It is demonstrated that human upper body shapes can be reconstructed to giga voxel resolution at greater than 30 fps on modern graphics hardware.
- Estimation of displacements from two 3D frames obtained from stereo78
A method for estimating 3D displacements from two stereo frames is presented, based on the hypothesize-and-verify paradigm used to match 3D line segments between the two frames, which is quite robust, fast, and has been thoroughly tested on hundreds of real stereo frames.
- 72
- Motion and structure from two perspective views: from essential parameters to Euclidean motion through the fundamental matrix71
The conjecture is that the imposition of the constraints arising from projective geometry should be used as an intermediate step to obtain reliable three-dimensional Euclidean motion and structure estimation from multiple calibrated images.
- Determining motion from 3D line segment matches: a comparative study69
A comparative study on motion estimation from 3D line segments is presented, using both synthetic and real data obtained by a trinocular stereo, and it is observed that the extended Kalman filter with the rotation axis representation of rotation is preferable.
- 68
- Token tracking in a cluttered scene68
Some strategies for tracking with emphasis on practical importance include beam search for resolving multiple matches, support of existence for discarding false matches, and locking on reliable tokens and maximizing local rigidity for handling combinatorial explosion are introduced.
- Generic HRTFs May be Good Enough in Virtual Reality. Improving Source Localization through Cross-Modal Plasticity65
The results show that pairing a dynamic auditory stimulus, with a spatio-temporally aligned visual counterpart, enabled users of generic HRTFs to improve subsequent auditory source localization.
- 65
- 64
- Computer Vision and Machine Learning with RGB-D Sensors63
This book presents an interdisciplinary selection of cutting-edge research on RGB-D based computer vision, and proposes a new classifier architecture for real-time hand pose recognition and a novel hand segmentation and gesture recognition system.
- 62
- Estimating the Fundamental Matrix by Transforming Image Points in Projective Space62
This paper proposes a novel technique for estimating the fundamental matrix by transforming the image points in projective space with one parameterization of the fundamental Matrix, rather than considering 36 distinct parameterizations as in previous work.
- A Progressive Scheme for Stereo Matching62
A progressive scheme for stereo matching which uses the disparity gradient limit principle and the least commitment strategy to select only the most reliable matches and postpone unreliable decisions until enough confidence is accumulated is proposed.
- Model-based hand pose estimation via spatial-temporal hand parsing and 3D fingertip localization59
Quantitative experiments on synthetic data show the proposed hand pose estimation scheme can accurately capture the natural hand motion, and a simulated water-oscillator application is built to demonstrate the effectiveness of the proposed method in human-computer interaction scenarios.
- 59
- 59
- 57
- ImmerseBoard: Immersive Telepresence Experience using a Digital Whiteboard56
User studies involving three tasks show that compared to standard video conferencing with a digital whiteboard, ImmerseBoard provides participants with a quantitatively better ability to estimate their remote partners' eye gaze direction, gesture direction, intention, and level of agreement.
- 54
- 53
- 53
- 51
- 48
- 48
- 47
- 46
- 45
- Explainable Hierarchical Imitation Learning for Robotic Drink Pouring44
The proposed Explainable Hierarchical Imitation Learning (EHIL) method enables the robot to learn a sequence of reasonable pouring phases for performing the task rather than simply execute the task via traditional behavior cloning, so explainability and safety can be ensured.
- 43
- 43
- A stereovision system for a planetary rover: calibration, correlation, registration, and fusion43
A new effective on-site calibration technique has been developed, which can make use of the information from the surrounding environment as well as the Information from the calibration apparatus, and a correlation-based stereo algorithm is used which can produce sufficient dense range maps with an algorithmic structure for fast implementations.
- 42
- A New Multistage Approach to Motion and Structure Estimation: From Essential Parameters to Euclidean Motion Via Fundamental Matrix42
The conjecture from this work is that the estimation of the uncalibrated epipolar geometry should be used as an intermediate step in order to obtain reliable 3D Euclidean motion and structure estimation from multiple calibrated images.
- 41
- 39
- Concurrent talking in immersive virtual reality: on the dominance of visual speech cues39
A disruption of selective attention that is triggered by bottom-up multisensory integration is revealed by using immersive Virtual Reality technologies with spatialized audio to study how auditory-visual cues modulate this selective listening.
- 39
- 37
- 37
- A Review of Intelligent Walking Support Robots: Aiding Sit-to-Stand Transition and Walking34
A comprehensive review of recent literature on Walking Support Robots, encompassing an analysis of structure design, perception methods, control strategies and safety & comfort features is offered.
- 34
- Digital Twin-Driven Mixed Reality Framework for Immersive Teleoperation With Haptic Rendering33
This study developed an immersive, bilateral teleoperation system, integrating Digital Twin-driven Mixed Reality manipulation with haptic rendering, which comprises a commercial remote controller with a kinaesthetic rendering feature and a wearable cost-effective tactile rendering interface, called the Soft Pneumatic Tactile Array (SPTA).
- 33
- Towards accurate and robust cross-ratio based gaze trackers through learning from simulation30
This paper introduces an adaptive homography mapping for achieving gaze prediction with higher accuracy at the calibration position and more robustness under head movements and shows that the method compares favorably against other state-of-the-art CR based methods.
- DA$^{2}$ Dataset: Toward Dexterity-Aware Dual-Arm Grasping29
DA, the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasping pairs for arbitrary large objects, is introduced and an end-to-end dual- arm grasp evaluation model trained on the rendered scenes from this dataset is proposed.
- Can Visual Recognition Benefit from Auxiliary Information in Training?29
This work proposes a collaborative auxiliary learning framework based on a new discriminative canonical correlation analysis that reveals a common semantic space shared across both views through enforcing a series of nonlinear projections.
- 29
- 29
- Exploring spatialized audio & video for distributed conversations28
This paper examined three-way distributed conversations while varying the presence of spatial video and audio to demonstrate significant benefits to adding spatialized video to an audio conference and suggest that the benefits of spatialized audio may have less of an impact when video is also spatialized.
- 28
- 27
- 27
- Model- and Exemplar-based Robust Head Pose Tracking Under Occlusion and Varying Expression27
This work presents a model- and exemplar-based technique for head pose tracking that automatically builds a personalized 3D face model by fitting a generic mesh model to a near frontal facial image, and acquires a few reference images at distinct poses to sparsely sample the facial appearance space.
- Compliance while resisting: A shear-thickening fluid controller for physical human-robot interaction26
- Improving cross-ratio-based eye tracking techniques by leveraging the binocular fixation constraint26
Experimental results show that the proposed cross-ratio approach produces significantly better results than using a single eye and also better than averaging the independent results from the two eyes.
- Boosting-Based Face Detection and Adaptation26
This book describes a boosting learning framework that is capable to handle billions of training examples, and presents a series of algorithms that are empowered by the statistical view of boosting and the concept of multiple instance learning.
- Multisensory processing for speech enhancement and magnitude-normalized spectra for speech modeling26
A new speech model based on statistics of magnitude-normalized complex spectra of speech signals is presented, able to get rid of huge intra- and inter-speaker variation in speech energy and to build a better speech model with a smaller number of Gaussian components.
- A General Expression of the Fundamental Matrix for Both Perspective and Affine Cameras26
A new technique for affine reconstruction from two affine images is developed, which consists in first estimating the affine epipolar geometry and then performing a triangulation for each point match with respect to an implicit common affine basis.
- Ground-Challenge: A Multi-sensor SLAM Dataset Focusing on Corner Cases for Ground Robots25
A challenging dataset comprising 36 trajectories with diverse corner cases such as aggressive motion, severe occlusion, changing illumination, motion blur, wheel suspension, etc, to support the research on corner cases of visual SLAM systems is presented.
- Guest Editorial Introduction to the Special Issue on Group and Crowd Behavior Analysis for Intelligent Multicamera Video Surveillance25
Group behavior analysis provides a novel level for describing events, which are semantically more meaningful, highlighting barely visible relational connections among people and for anomaly detection such as panic scenarios, dangerous situations, and illegal behaviors in public spaces.
- Image-based modeling of objects and human faces25
An overview of the project on 3D object and face modeling from images taken by a free-moving camera, which briefly covers the following topics: camera calibration, stereo rectification, image matching, 3D photo editing, object modeling, and face modeled.
- An Effective Technique for Calibrating a Binocular Stereo Through Projective Reconstruction Using Both a Calibration Object and the Environment25
Videre: Journal of Computer Vision Research is a quarterly journal published electronically on the Internet by The MIT Press, Cambridge, Massachusetts, 02142 and prices subject to change without notice.
- 24
- 24
- Mining partially annotated images24
The Semi-Supervised Correspondence Hierarchical Dirichlet Process (SSCHDP) is proposed, which lies in exploiting the information pertaining to partially annotated images or even unannotated images to achieve semi-supervised learning under the HDP structure.
- Multiscale haptic interfaces for metaverse23
A wearable haptic feedback device made of thermoplastic urethanes with an adjustable pneumatic haptic interface (PHI) that contains actuator types of different sizes and layouts to provide haptic feedback ranging from delicate and precise feedback to robust and large-area feedback.
- Requirements and recommendations for an enhanced meeting viewing experience23
A 3D interface prototype is presented designed specifically to provide speaker-related information and more control of the interface, including changing the relative sizes of the speaker and context views and navigating within the context view when viewing recorded meetings.
- 23
- Rapid modeling of animated faces from video images23
This work has developed a system that constructs textured 3D face models from videos with minimal user interaction, and this system will demonstrate the system at the conference.
- Feature-Based Facial Expression Recognition: Experiments With a Multi-Layer Perceptron23
Experiments show that facial expression recognition is mainly a low frequency process, and a spatial resolution of 64 pixels $\times$ 64 pixels is probably enough, and the significance of image scales is studied.
- 22
- 21
- What did i miss?21
An Accelerated Instant Replay (AIR) Conferencing system for videoconferencing that enables users to catch up on missed content while the meeting is ongoing and preferred using audio along with any other modality to using audio alone.
- Introduction to the Special Issue on Mobile Vision21
The ubiquity of high quality mobile cameras with ever increasing computational capacity, packaged along with other rich sensors, is providing many new opportunities for applications of computer vision technologies, especially those that support human activities such as location-based and usercentered services.
- 20
- 20
- Semantic action recognition by learning a pose lexicon20
The efficacy of the proposed semantic representation, pose lexicon, for action recognition was evaluated on MSRC-12, WorkoutSU-10, workoutUOW-18, Combined-15 and Combined-17 action datasets using cross-subject, cross-dataset and zero-shot protocols.
- Auxiliary Training Information Assisted Visual Recognition20
This paper proposes a collaborative auxiliary learning framework based on a new discriminative canonical correlation analysis that reveals a common semantic space shared across both modalities/views through enforcing a series of nonlinear projections.
- 20
- 20
- 20
- Intent inference in shared-control teleoperation system in consideration of user behavior19
A probabilistic formulation for inferring the user intent by taking consideration of user behavior is presented and it is shown that the proposed approaches outperform the existing methods especially in scenarios with goal ambiguity.
- Speeding up spatio-temporal sliding-window search for efficient event detection in crowded videos19
This work proposes a heuristic branch-and-bound solution for event detection in videos by directly finding subvolumes whose scores are higher than the threshold, which dramatically reduces computational cost without significantly degrading the quality of the detection results.
- Efficient Scale-Space Spatiotemporal Saliency Tracking for Distortion-Free Video Retargeting18
This paper proposes a novel approach to distortion-free video retargeting by scale-space spatiotemporal saliency tracking, and develops an efficient coarse-to-fine solution that combines exhaustive coarse and gradient-based fine search.
- Winner-Take-All Multiple Category Boosting for Multi-view Face Detection18
By allowing examples to self-organize themselves in such a winner-takeall manner, WTA-McBoost outperforms traditional schemes significantly, as supported by experiments on learning a multi-view face detector.
- 18
- Camera Calibration17
In this homework, the homography matrices between the captured images and the calibration pattern on the model plane should be available and the corner point detection procedures for the captured image are explained.
- Virtual View Generation with a Hybrid Camera Array17
This paper proposes a scheme based on a hybrid camera array consisting of four regular video cameras and one time-of-flight depth camera that demonstrates great potential in reducing the amount of data for compression/streaming while maintaining high rendering quality.
- A graphical model for multi-sensory speech processing in air-and-bone conductive microphones17
This paper proposes a graphical model based approach to estimating the clean speech signal given the noisy observations in the air sensor and shows how the same model can be used as a speech/non-speech classifier.
- 16
- 16
- 16
- New Measurements and Corner-Guidance for Curve Matching with Probabilistic Relaxation16
A new algorithm for curve matching (including lines) within a probabilistic relaxation framework, and an approach of incorporating previously matched points/corners to guide curve matching are described.
- Finding clusters and planes from 3D line segments with application to 3D motion determination16
An algorithm based on the hypothesize-and-verify paradigm to register two consecutive 3D frames and estimate their transformation/motion can be developed to reduce effectively the complexity of the hypothesis generation phase.
- 15
- 15
- Camera calibration: a personal retrospective15
3D computer vision is a subfield of computer vision that focuses on extracting 3D metric information from 2D images, which is a very challenging task since what the authors have in an image is the projection of a 3D scene, whose depth information is lost during image formation (image projection).
- 15
- 15
- Model-based fusion of bone and air sensors for speech enhancement and robust speech recognition.15
A probabilistic framework that uses a bone sensor and air microphone to perform speech enhancement for robust speech recognition and demonstrates considerable improvements in recognition for four subjects on a difficult condition with background speaker interference.
- 15
- 14
- 14
- A new multistage approach to motion and structure estimation by gradually enforcing geometric constraints14
The conjecture from this work is that the imposition of the constraints arising from projective geometry should be used as an intermediate step in order to obtain reliable 3D Euclidean motion and structure estimation from multiple calibrated images.
- 14
- 13
- 13
- 13
- 13
- New lower bounds of fifteen classical Ramsey numbers.13
An algorithm to compute lower bounds for the classical Ramsey numbers R(Ql' Q2," " Qn) is developed and fifteen new lower bounds are obtained, of which eight are for multicolor Ramsey numbers and the other seven (which have been quoted by Radziszowski [11]) are for 2-color ones.
- 12
- Vision-based Interaction with Fingers and Papers12
This paper presents two vision-based interface systems that use an inexpensive technique to transform an ordinary screen into a touch screen using an ordinary camera and employs an arbitrary quadrangle-shaped panel and a tip pointer as an intuitive, wireless and mobile input device.
- From an ordinary paper to a wireless and mobile input device12
This paper presents a vision-based gesture interface system, VISUAL PANEL, which employs an arbitrary quadrangle-shaped panel and a tip pointer as an intuitive input device that can accurately and reliably track the panel and the tip pointer.
- VISUAL PANEL: From an ordinary paper to a wireless and mobile input device12
This paper presents a vision-based gesture interface system, VISUAL PANEL, which employs an arbitrary quadrangle-shaped panel and a tip pointer as an intuitive input device that can accurately and reliably track the panel and the tip pointer.
- 11
- 11
- 11
- Modeling and representing events in multimedia11
An overview of the Joint Workshop on Modeling and Representing Events (JMRE) is presented, which is concerned with the understanding of events from multimedia, and with using events in order to better organize and consume multimedia.
- 11
- 11
- Obstacle Avoidance and Trajectory Planning for an Indoor Mobile Robot Using Stereo Vision and Delaunay Triangulation11
This article describes the work at INRIA on obstacle avoidance and trajectory planning for a mobile robot using stereo vision, equipped with a trinocular vision system that is being put into hardware and capable of delivering 3-D maps of the environment at rates between 1 and 5 Hz.
- 10
- 10
- Towards ideal window layouts for multi-party, gaze-aware desktop videoconferencing10
An exploration of user preferences and their interplay with previously established window layout guidelines is presented and five recommendations for user-preferred window layouts in high-end desktop videoconferencing systems are created.
- 10
- 10
- 10
- A Unified Theory of Uncalibrated Stereo for Both Perspective and Affine Cameras10
A new technique for affine reconstruction is developed, which consists in first estimating the affine epipolar geometry and then performing a triangulation for each point match with respect to an implicit common affine basis.
- An automatic and robust algorithm for determining motion and structure from two perspective images10
A very robust technique, namely the least-median-squares, is used to detect false matches in the motion space with which most of matches satisfy the well-known coplanarity constraint and the proposed algorithm is completely automatic.
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- Multi-view learning from imperfect tagging8
A novel discriminative classification method is proposed under the framework of MITL, which explicitly makes use of the given multiple labels simultaneously as an additional feature to deliver a more effective classification performance than the existing literature where one label is considered at a time as the classification target.
- Mining noisy tagging from multi-label space8
It is argued that all the given multiple tags can be utilized simultaneously as an additional feature and the information contained in the multi-label space can be taken advantage of to improve the performance of the classification.
- AIR conferencing8
An Accelerated Instant Replay (AIR) Conferencing system for videoconferencing that enables participants to privately catch up to an ongoing meeting and explored several mechanisms where the meeting content is replayed at an accelerated rate so that the participants cancatch up to the live discussion reasonably quickly.
- MobileSurface8
A virtual interactive surface technology based on a projector-camera system connected to a mobile device that can project images on any free surfaces and enable interaction in the air within the projection area is described.
- Autonomous Mental Development: A New Interdisciplinary Transactions for Natural and Artificial Intelligence8
In recognition of the gains made in this field and to support its further development, the IEEE has approved this new IEEE TRANSACTIONS on Autonomous Mental Development (TAMD).
- Frequency domain correspondence for speaker normalization8
A novel data-driven framework is proposed to build the alignment of the frequency axes of two speakers by forming a frequency domain correspondence of these two speakers as an optimal matching problem.
- Re-rendering from a Sparse Set of Images8
A method to accomplish photorealistic rendering of real-world objects from their sparsely sampled appearance variation using a 3D model and a small set of images to recover all the necessary photometric information for subsequent rendering from arbitrary viewpoints and under novel lighting conditions is presented.
- Visual Screen: Transforming an Ordinary Screen into a Touch Screen8
An image-screen mapping algorithm to correct the non-flatness of the computer screen and a segmentation method specially tailored for computer screen background are proposed.
- TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs7
This work provides a standardized methodology to evaluate human alignment in LLMs for both English and Chinese, and constructs a hierarchical task tree encompassing seven major areas covering over 200 categories and over 800 tasks, to evaluate LLMs in a comprehensive and in-depth manner.
- 7
- A Stereovision-based navigation system for a mobile robot7
This report describes the work at INRIA on obstacle avoidance and trajectory planning for a mobile robot using stereovision, and shows examples in which the robot navigates freely in a real indoors environment using this system.
- 7
- 6
- 6
- 6
- 6
- 6
- Face Geometry and Appearance Modeling6
This book provides a systematic description of modeling face geometry and appearance from images, including information on mathematical tools, physical concepts, image processing and computer vision techniques, and concrete prototype systems.
- 6
- 6
- Motion of a stereo rig: Strong, weak and self calibration6
This paper addresses different issues of motion analysis with stereovision with respect to strongly calibrated and weakly calibrated stereo systems.
- 6
- Strategies for Tracking Tokens in a Cluttered Scene6
Some strategies for tracking with emphasis on practical importance include beam search for resolving multiple matches, support of existence for discarding false matches, and locking on reliable tokens and maximizing local rigidity for handling combinatorial explosion are described.
- 5
- High-Fidelity 3D Digital Human Creation from RGB-D Selfies5
A new facial geometry modeling and reflectance synthesis procedure that significantly improves the state-of-the-art and has much larger expressive capacities than conventional 3DMM, allowing us to recover more accurate facial geometry using merely linear bases.
- 5
- 5
- Multichannel Acoustic Echo Cancellation in Multiparty Spatial Audio Conferencing with Constrained Kalman Filtering5
Experimental results show the proposed AEC algorithm has much higher performance than the scheme proposed in [1] which uses NLMS as the adaptive filter and does not explore the available constraint.
- A Complete Navigation System for a Mobile Robot, Using Real-Time Stereovision and the Delaunay Triangulation.5
The trinocular vision system that has been put into hardware and delivers 3D maps of the environment at a rate between 1 and 5Hz helps to locate the obstacles and plan a safe trajectory around the mobile robot.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- Point matching for registration of free-form surfaces4
A method has been developed for registering two dense 3-D maps obtained by using a correlation-based stereo system based on iteratively matching points of one view to the closest points of the another view, which yields an accurate motion estimate.
- Uncertainty Manipulation and Parameter Estimation4
It is very important to explicitly manipulate the uncertainty of measurements, because the observations made by a sensor are always corrupted by noise.
- 3
- 3
- Completed Dense Scene Flow in RGB-D Space3
A completed dense scene flow framework is proposed, which models both rotation and translation for general motion estimation and outperforms other published methods on the RGB-D image space.
- Vision-enhanced Immersive Interaction and Remote Collaboration with Large Touch Displays3
A system that enables natural interaction and immersive remote collaboration with large touch displays by adding a commodity color plus depth sensor and provides participants with a quantitatively better ability to estimate their remote partners' eye gaze direction, gesture direction, intention, and level of agreement.
- 3
- 3
- 3
- 3
- Action Detection by Fusing Hierarchically Filtered Motion with Spatiotemporal Interest Point Features3
This chapter proposes a new approach which combines Gaussian Mixture Models (GMMs) with Branch-and-Bound search to locate interested actions in cluttered videos and demonstrates that the proposed method significantly outperforms existing techniques especially for action detection in crowded videos.
- Face Geometry and Appearance Modeling: Concepts and Applications3
This book provides a systematic description of modeling face geometry and appearance from images, including information on mathematical tools, physical concepts, image processing and computer vision techniques, and concrete prototype systems.
- A Tighter Lower Bound on the Spetsakis–Aloimonos Trilinear Constraints3
This note shows that there in fact exists four independent equations for point match between three views in the linear algorithm, and has an important consequence: the minimum number of points required for thelinear algorithm is seven instead of nine.
- Camera Models and Epipolar Geometry3
This chapter presents a detailed description of the epipolar geometry between two images taken by two different cameras or by a single camera at two different time instants.
- 1 - Recalage de deux nuages de points 3D3
A method has been developed for registering two dense 3-D maps obtained by using a correlation-based stereo system that is efficient and robust, and yields an accurate motion estimate.
- 2
- 2
- Essential Matrix2
Binocular stereo is addressed, where there is a similar constraint in binocular stereo – namely that constrains corresponding points to lie on a line.
- 2
- 2
- 2
- 2
- 2
- Human Action Recognition with Expandable Graphical Models2
Human motion analysis has attracted increasing attention in the past decade due to its scientific challenges and social and economic significance in a wide range of applications including video surveillance for home, workplace and public environment, human computer interface, and study and diagnosis of movement disorder.
- CIS Publication Spotlight [Publication Spotlight]2
An incremental nonnegative matrix factorization (NMF) with volume constraint is derived and utilized for solving online BSS, which can be used to separate correlative sources and performs especially well in the recovery of dependent sources.
- 2
- 2
- Remote Collaboration on Physical Whiteboards2
This paper presents the work in developing tools to facilitate collaboration on physical whiteboards by using a camera and a microphone, which allows a user to take notes of a whiteboard meeting when he/she wants or in an automatic way, and to archive the whole whiteboard session for efficient post-viewing.
- Side Statistics and Maximum Discriminant Analysis for Real-Time Tracking2
A new technique for tracking based on side statistics and maximum discriminant analysis that can deal with complex environment, changing background, and partial occlusion, and it is real-time and accurate is proposed.
- A Robust and Fast Face Modeling System2
This paper describes a face modeling system which allows a user, with a PC and an ordinary video camera, to construct their own 3D face models with minimal manual work, and the constructed face model can be animated right away.
- 2
- 2
- 2
- Motion analysis of two stereo views and its applications2
An algorithm based on the Hypothesize-and-Verify paradigm is presented to register two stereo frames taken while a mobile robot navigates in an indoor environment with rigidity constraints complete for 3D line segments.
- Harnessing machine learning and AI-driven analytics to identify novel drug targets and predict chemotherapy efficacy in NSCLC1
An all-inclusive model combining clinical data, AI-derived variables, and mtRNA biomarkers produced a risk score capable of discriminating patients into high- and low-risk groups for progression-free survival and overall survival, with statistically significant differences observed between these groups.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Digital Human in an Integrated Physical-Digital World (IPhD)1
This talk will describe the work on digital human for this IPhD world, which includes: computer vision techniques for building digital humans, multimodal text-to-speech synthesis (voice and lip shapes), speech-driven face animation, neural-network-based body motion control, human-digital-human interaction, and an emotional video game anchor.
- Whiteboard Scanning: Get a High-res Scan With an Inexpensive Camera1
The Whiteboard Scanning system captures either a set of snapshots with overlap or a continuous video sequence, and then stitches them automatically into a single high-res image, which can be exported to the Whiteboard It! system for further enhancement.
- 1
- 1
- 1
- 1
- Affine Projection1
This paper addresses a fast affine projection algorithm to deploy on the stereo acoustic echo canceler, and its major role is to produce the echo replica.
- 1
- Societally connected multimedia across cultures1
This position paper proposes to define a new research area called ‘connected multimedia’, which is the study of a collection of research issues of the super-area social media that receive little attention in the literature.
- 1
- Guest Editors' Introduction: Special Section on Connected Multimedia1
This editorial is co-authored by the guest-editors who also organized the two editions of the workshop on the newly emerged theme of connected multimedia held in Hangzhou, China and in Florence, Italy, in October, 2010.
- 1
- Innovating the multimedia experience1
In this panel, each panelist will present their view of the current state-of-the-art of research and product innovations in the three major areas of multimedia experience: visual, auditory and gaming.
- 1
- Overview of ACM international workshop on connected multimedia1
In this workshop overview, what is meant by connected multimedia is defined, and the program of this workshop is briefly overviewed.
- 1
- 1
- 1
- 1
- A novel framework of text-independent speaker verification based on utterance transform and iterative cohort modeling1
The novel framework for text-independent speaker verification clearly shows that the iterative cohort modeling effectively reduce the data dependence of the final scores, so that T-Norm will not further improve the system performance.
- Fusing Array Microphone and Stereo Vision for Improved Computer Interfaces1
This work describes how computer vision may be used in combination with an array microphone to improve speech recognition accuracy in the context of noise, and proposes to use computer vision to help determine the location of the user, and infer whether he is talking to the computer.
- Curve Matching with Probabilistic Relaxation.1
The 1riai11 corltribution in this paper is to propose a new algorithr~i for curve matching (illcludi~lg lines) and the nlethod is described within a probabilistic relaxatio~l fra~rlework.
- Recovery of Epipolar Geometry from Points1
This chapter presents a number of methods to recover the epipolar geometry between two images from point matches, and at least-squares techniques are exploited to obtain a more robust estimate.
- Hypothesize-and-Verify Method for Two 3D View Motion Analysis1
This chapter presents a method based on the hypothesize-and-verify paradigm to register two sets of 3D line segments obtained from stereo and to Computerte the transformation (motion) between them.
- 1
- Implementation Details and Experimental Results1
This chapter develops the token tracking technique with which to integrate the formulation developed in Chap.
- Solving the Motion Tracking Problem: A Framework1
This work has shown that using long sequences of frames shows its advantage in the two-view motion analysis, particularly when more information is used and some minimization algorithms are required.
- Object Recognition and Localization1
This paper aims to adapt the motion-determination algorithm developed in Chap.
- Tactile physical human–robot interaction: a continuous coupling paradigm for walking assistance–
It is shown that large-area tactile coupling at the human torso provides a physically grounded channel through which intention alignment and stability support are intrinsically unified, and suggests torso-level tactile coupling offers a principled pathway toward safer, more cooperative physical human-robot interaction.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Challenges of Multimodal Interaction in the Era of Human-Robot Coexistence–
With the rapid progress in computing and sensory technologies, the era of human-robot coexistence in the not-too-distant future is entered, and it is time to address the challenges of multimodal interaction.
- Share or Split : which is more efficient?–
Two different feature representations in convolutional neural networks (CNN): Share all classes share the same feature space, and a fully connected layer is used to decode class activation, and Split each class has its own feature space and a class is activated if its corresponding feature vector has a large norm.
- –
- Visual Understanding with RGB-D Sensors–
This special issue is specifically dedicated to new algorithms and applications based on the Kinect sensors, and serves as a convincing forum for researchers and practitioners to disseminate their latest research on visual understanding with RGB-D sensors.
- –
- –
- –
- –
- –
- –
- –
- –
- Depth Distortion–
If you really want to be smarter, reading can be one of the lots ways to evoke and realize.
- –
- –
- –
- Developmental Learning for User Activities–
This chapter presents a brain-inspired developmental learning system that enables it to learn sensorimotor association (which is tractable), and the real-time prototype system has been tested in different office environments.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Introduction to the ICME2010 Special Issue–
The 15 papers in this special issue are extended versions of papers presented at the 2010 IEEE International Conference on Multimedia and Expo (ICME), held in Singapore on July 19-23, 2010.
- –
- –
- –
- –
- –
- –
- Speaker authentication using adapted background models–
Speaker authentication is performed by determining a similarity score for a test utterance and a stored training utterance by determining the product of a posterior probability of a mixture component and a difference between an adapted mean and a background mean.
- –
- –
- –
- –
- Audio-visual analysis for event understanding–
This talk will focus on event understanding using audio and visual information either separately or jointly on presence detection in an office environment using multi-sensory inputs from streams of video, audio and computer interactions.
- –
- –
- –
- –
- –
- Software-based distortion compensation for a scanned beam display–
A software-based approach to compensate for distortion in a scanned beam display (SBD) system by minimizing the difference between input and output images on a software level and implemented the algorithm on Graphics Processing Unit to achieve near real-time performance which is required by video display.
- –
- Editorial–
This special issue contains five revised and expanded papers selected from the Sixth Asian Conference on Computer Vision (ACCV2004) and seven papers from ACCV2004 selected for the special issue of International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI).
- –
- Panel Session on Computations and Algorithms–
The topic of this first panel session was algorithms and computations and each panelist discussed the issues that he felt were going to be important in the future.
- –
- Image Matching and Uncalibrated Stereo–
Developing a robust image matching technique is very important as the difficulty is partly bypassed by taking long sequences of images over short time interval and as the time interval is small and object velocity is constrained by physical laws.
- 3D Object Recognition and Localization with Model Views–
The conventional approaches to 3D object recognition are mostly based on3D object models, which rely on explicit 3D data as object model in this or that way, but these are not always available for every object.
- Multiple Rigid Motions: Correspondence and Segmentation–
Segmentation of motion images into different rigid objects has to be solved in the case of multiple motions for both correct correspondence and structure-from-motion computation.
- Recovery of Epipolar Geometry from Line Segments or Straight Lines–
Two types of geometric primitives have been used in solving motion and structure problem, namely points and straight lines, and the overlook of line segments in the domain ofmotion and structure from motion is probably due to the lack of mathematical elegance in representing line segments.
- A Comparative Study of 3D Motion Estimation–
The motion analysis problem is usually divided into two subproblems: correspondence of primitives and estimation of motion, usually in that order.
- Reconstruction of 3D Line Segments–
The work described in this monograph should be applicable to 3D data obtained from various different sources, but is especially interested in 3DData from stereo, particularly 3D line segments.
- Further Considerations on Reducing Complexity–
This chapter describes in the last chapter a method based on the hypothesize- verify- verify paradigm for registering two 3D frames obtained from stereo and Computerting their motion (transformation).
- Modeling and Estimating Motion Kinematics–
In this chapter, the well-known model of classical rigid-bodies kinematics is described and the closed-form solutions for some special motions are derived and used to solve the motion tracking problem by the EKF.
- Fusing Multiple 3D Frames–
This chapter focuses on how to fuse multiple 3D frames obtained by a stereo system and builds automatically and incrementally a model of an unknown environment.
- Matching and Rigidity Constraints–
In mobile robot navigation, the robot must determine its displacement between successive positions and perhaps find its position relative to a world reference and many others involve the problem of matching and motion/ pose determination.
- Multiple Object Motions–
The motion analysis of two frames in which there is only one moving object can be solved to solve the following two problems.
- Representations of Geometric Objects–
This chapter studies the representations of the geometric objects which are encountered in the application of 3D vision and robotics and includes rigid motion and line segments.
- Calibrating a Mobile Robot and Visual Navigation–
This chapter addresses the calibration problem between the stereo and odometric systems of the INRIA mobile robot, which is essential for many applications, including visual navigation.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.