Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks73 from public data
- PieAPP: Perceptual Image-Error Assessment Through Pairwise Preference396
A new learning-based method that is the first to predict perceptual image error like human observers, and significantly outperforms existing algorithms, beating the state-of-the-art by almost 3× on the authors' test set in terms of binary error rate, while also generalizing to new kinds of distortions, unlike previous learning- based methods.
- PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models168
This paper explores an alternative way for low-shot part segmentation of 3D point clouds by leveraging a pretrained image-language model, GLIP, which achieves superior performance on open-vocabulary 2D detection and a novel 2D-to-3D label lifting algorithm.
- 123
- XModal-ID: Using WiFi for Through-Wall Person Identification from Candidate Video Footage101
Results show that XModal-ID can robustly identify new people walking in new environments, in various practical scenarios.
- 67
- X-Align++: cross-modal cross-view alignment for Bird’s-eye-view segmentation55
This paper proposes X-Align, a novel end-to-end cross-modal and cross-view learning framework for BEV segmentation consisting of a novel Cross-Modal Feature Alignment (X-FA) loss, and provides extensive ablation studies to demonstrate the effectiveness of the individual components.
- AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation50
An efficient, intuitive, and unsupervised online adaptation method, AuxAdapt, for improving the temporal consistency of most neural network models, which does not require optical flow and only takes one pass of the video.
- Teaching RF to Sense without RF Training Measurements48
This paper proposes a novel, generalizable, and scalable idea that eliminates the need for collecting Radio Frequency (RF) measurements, when training RF sensing systems for human-motion-related activities, and can successfully train an RF sensing system without any real RF measurements.
- 45
- MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation33
MAMo is proposed, a novel memory and attention framework for monocular video depth estimation that consistently improves monocular depth estimation networks and sets new state-of-the-art (SOTA) accuracy.
- 33
- Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation32
The Factorized Inverse Path Tracing (FIPT) addresses challenges by using a factored light transport formulation and finds emitters driven by rendering errors, and enables accurate material and lighting optimization faster than previous work, and is more effective at resolving ambiguities.
- EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation27
A novel guided attention architecture, EGA-Depth, which can improve both the efficiency and accuracy of self-supervised multi-camera depth estimation by using its perspective view as the query to cross-reference its neighboring views to derive informative features for this camera view.
- OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation24
This work proposes OCAI, a method that supports robust frame interpolation by generating intermediate video frames along-side optical flows in between and introduces a teacher-student style semi-supervised learning method on top of the interpolated frames.
- X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation24
A novel method to improve the self-supervised training of monocular depth via cross-task knowledge distillation from semantic segmentation to depth estimation, which significantly improves the depth estimation accuracy and outperforms the state of the art.
- Motion and communication co-optimization with path planning and online channel prediction24
An in-house algorithm is utilized that computes near-optimal solutions in little time and enables its use in the online setting, and the optimization strategy is described in detail and validated by simulation of realistic scenarios.
- 22
- 22
- DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling21
A novel data augmentation approach for training optical flow estimation models by introducing realistic distractions to the input frames by combining one of the frames in the pair with a distractor image depicting a similar domain, which allows for inducing visual perturbations congruent with natural objects and scenes.
- 4D Panoptic Segmentation as Invariant and Equivariant Field Prediction21
This paper develops rotation-equivariant neural networks for 4D panoptic segmentation and sets the new state-of-the-art performance and achieves 1st place on the SemanticKITTI 4D Panoptic Segmentation leaderboard.
- HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation20
This paper proposes Hierarchically Supervised Semantic Segmentation (HS3), a training scheme that supervises intermediate layers in a segmentation network to learn meaningful representations by varying task complexity, and devise a fusion framework, HS3-Fuse, to aggregate the hierarchical features generated by these layers.
- 20
- Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentation19
This paper presents a novel framework to integrate both semantic and instance contexts for panoptic segmentation, and proposes a novel Panoptic, Instance, and Semantic Relations (PISR) module to exploit such contexts.
- Perceptual Consistency in Video Segmentation19
A novel perceptual consistency perspective on video semantic segmentation is presented, which can capture both temporal consistency and pixel-wise correctness and be used as a regularizer during the training of segmentation models, which leads to more temporally consistent video segmentation while maintaining accuracy.
- 14
- 14
- 13
- 12
- Planar Gaussian Splatting11
Planar Gaussian Splatting achieves state-of-the-art performance in 3D planar reconstruction without requiring either 3D plane labels or depth supervision, and maintains its performance across datasets thanks to its neural rendering and scene-specific optimization mechanism.
- 11
- PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer9
PADRe runs significantly faster than the conventional self-attention while maintaining similar accuracy when substituting self-attention in the transformer models, and is assessed as a drop-in replacement for self-attention across diverse computer vision tasks.
- Question Recommendation in Medical Community-Based Question Answering8
A Siamese CNN model which measure correlation between questions and answers is proposed and can effectively extract similar questions recommendation list, shorten user’s time to wait for an answer and improve user experience as well.
- 8
- 7
- Communication-Aware RRT*: Path Planning for Robotic Communication Operation in Obstacle Environments7
- Transadapt: A Transformative Framework for Online Test Time Adaptive Semantic Segmentation6
This work proposes TransAdapt, a framework that uses transformer and input transformations to improve segmentation performance in online settings and pre-train a transformer-based module on a segmentation network that transforms unsupervised segmentation output to a more reliable supervised output, without requiring test-time online training.
- 6
- 6
- 5
- Asking for Help with the Right Question by Predicting Human Visual Performance5
A machine learning-based approach that allows the robot to probabilistically predict human visual performance for any visual input is proposed and presented, indicating a considerable increase in the success rate of human queries and the overall performance.
- An Image Segmentation Method Using Image Enhancement and PCNN with Adaptive Parameters5
Experimental results show that image segmentsation using image enhancement and PCNN with adaptive parameters is significantly better than the traditional PCNN image segmentation and verify the effectiveness of the method.
- 5
- H3O: Hyper-Efficient 3D Occupancy Prediction with Heterogeneous Supervision4
This paper presents a novel 3D occupancy prediction approach, H30, which features highly efficient architecture designs that incur a significantly lower computational cost as compared to the current state-of-the-art methods.
- 4
- ISAR target recognition based on manifold learning4
The proposed method has the capability of finding the low-dimensional manifold structure embedded in the high-dimensional ISAR image space controlled by few parameters, such as attitude angle, scale and position, etc., and better classification performance is acquired comparing to PCA and LDA.
- DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos3
DySS leverages a state-space model (SSM) to sequentially process the sampled features over time steps and dynamically update the queries via merge, remove, and split operations, which help maintain a useful, lean set of detection queries throughout the network.
- GBS-Assisted Quantum Unsupervised Machine Learning on a Universal Programmable Integrated Quantum Chip3
The first experimental implementation of quantum unsupervised machine learning using the GBS protocol with a universal programmable integrated photonic chip is presented, demonstrating quantum-enhanced capability in extracting complex features from high-dimensional spaces and improved performance in generating arbitrary curve points and reconstructing handwritten digit images.
- FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices3
This paper proposes FALO, a hardware-friendly approach to LiDAR 3D detection, which offers both state-of-the-art (SOTA) detection accuracy and fast inference speed and can readily deploy on compact, embedded devices.
- 3
- SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations3
Two synergistic techniques, Self-Cleaning Iteration (SCI) and Regression Focal Loss (RFL), designed to enhance the capabilities of optical flow models, with a focus on addressing optical flow regression ambiguities, prove particularly effective in mitigating error propagation.
- A Shallow Neural Network Based Short Text Classifier for Medical Community Question Answering System3
- 3
- 3
- Gaussian Splatting is an Effective Data Generator for 3D Object Detection2
It is shown that generating hard examples, either by maximizing detection loss or imposing high visual occlusion in camera images, does not lead to more efficient 3D data augmentation for camera-based 3D object detection in autonomous driving.
- ISAR Target Recognition Based on Two-dimensional Locality Preserving Projection2
A novel ISAR target recognition algorithm is presented by using two-dimensional Locality Preserving Projections (2DLPP), which is based directly on 2D ISAR images rather than 1D vectors as conventional LPP does.
- When Human Visual Performance Is Imperfect—How to Optimize the Collaboration Between One Human Operator and Multiple Field Robots2
This chapter considers a robotic field exploration and classification task where the field robots have a limited communication with a remote human operator, and also have constrained motion energy budgets, and shows how multiple robots can properly optimize motion, sensing, and seeking help.
- Metrical Consistency NMF for Predicting Gene–Phenotype Associations2
A novel metrical consistency NMF (MCNMF) method for candidate gene prioritization that can recover the gene–phenotype associations effectively and outperform the comparative methods.
- 2
- 2
- 1
- HLA: Hadamard Linear Attention1
Unlike previous works on linear attention, the nonlinearity in HLA is not applied separately to queries and keys, but, analogously to standard softmax attention, after the pairwise similarities have been computed.
- Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties1
The Occlusion Avoiding (OA) loss is proposed, designed to guide the network into cycle consistency-based confident regions, where feature matching is more reliable and effectively manage various types of challenging pixels and regions during training.
- –
- –
- –
- –
- –
- Analysis and evaluation of regression model for centrifugal chiller–
Experimental results show that the Linear Regression Model and Support Vectorregression Model have excellent prediction performance, while BP Neural Network Regression model has serious over-fitting problem.
- The Research of Indoor Positioning Based on Double Wireless Access Points–
A method based on the result of weighted calculation using the positioning of two wireless access points to solve the problem of low accuracy of indoor positioning by singular wireless access point is proposed.
- QoS Routing Algorithm Using Competitive PCNN–
The problem of multi-constrained QoS routing is successfully solved using the properties of pulse wave parallel propagation of the competitive PCNN and the algorithm shows better computational performance and dominance and has important significance in both theory and applications.
- Face Detection Method Using PCNN and Skin Color Model–
This paper presented a face detection method for the color image using pulse coupled neural network (PCNN) and skin color model, which has higher accuracy and robustness, and can obtain satisfactory detection effect.
- –
- –
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.