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
- Weiping LiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works404 from public data
- 2,617
- 1,147
- Automatic salient object segmentation based on context and shape prior497
A novel automatic salient object segmentation algorithm which integrates both bottom-up salient stimuli and object-level shape prior, leading to binary segmentation of the salient object.
- 473
- A framework for efficient progressive fine granularity scalable video coding312
Experimental results show that the PFGS framework can improve the coding efficiency up to more than 1 dB over the FGS scheme in terms of average PSNR, yet still keeps all the original properties, such as fine granularity, bandwidth adaptation, and error recovery.
- Shape-adaptive discrete wavelet transforms for arbitrarily shaped visual object coding264
Comparison of shape-adaptive wavelet coding with other coding schemes for arbitrarily shaped visual objects shows that shape- Adaptive Wavelet coding always achieves better coding efficiency than other schemes.
- Descriptive visual words and visual phrases for image applications254
DVWs and DVPs are proposed as the visual correspondences to text words and phrases, where visual phrases refer to the frequently co-occurring visual word pairs, and are more comparable with the text words than the classic visual words.
- 245
- Multimedia search reranking228
Categorize and evaluate algorithms for visual search reranking, which reorders visual documents based on multimodal cues to improve initial text-only searches, and discuss relevant issues such as data collection, evaluation metrics, and benchmarking.
- 223
- 186
- Flickr distance183
Both subjective user study and objective evaluation show that Flickr distance is more coherent to human perception than Google distance, which makes it a more reasonable distance metric.
- Three-Dimensional Embedded Subband Coding with Optimized Truncation (3-D ESCOT)183
An efficient video coding algorithm: Three-dimensional embedded subband coding with optimized truncation (3-D ESCOT), in which coefficients in different subbands are independently coded using fractional bit-plane coding and candidate truncation points are formed at the end of each fractionalbit-plane.
- Virtualized Screen: A Third Element for Cloud–Mobile Convergence170
Two novel cloud-mobile applications, Cloud Browser and Cloud Phone, are presented to demonstrate the advantages of a virtualized screen, and technical challenges are discussed and addressed.
- 168
- 137
- 136
- 131
- Optimized Cartesian K-Means122
This paper proposes a novel approach, named optimized cartesian K-means (ock-mean), to better encode the data points for more accurate approximate nearest neighbor search, which can provide more flexibility and lower distortion errors than traditional methods.
- 122
- Order preserving hashing for approximate nearest neighbor search120
A novel method to learn similarity-preserving hash functions for approximate nearest neighbor (NN) search by maximizing the alignment between the similarity orders computed from the original space and the ones in the hamming space.
- VideoSense120
A novel advertising system for online video service called VideoSense, which automatically associates the most relevant video ads with online videos and seamlessly inserts the ads at the most appropriate positions within each individual video, is presented.
- Automatic Generation of Visual-Textual Presentation Layout114
This article presents a system to automatically generate visual-textual presentation layouts by investigating a set of aesthetic design principles, through which an average user can easily create visually appealing layouts, and demonstrates that the designs achieve the best reading experience compared with the reimplementation of parts of existing state-of-the-art designs.
- Contextual Video Recommendation by Multimodal Relevance and User Feedback114
VideoReach represents one of the first attempts toward contextual recommendation driven by video content and user click-through, without assuming a sufficient collection of user profiles available, and is designed to seamlessly integrate both multimodal relevance and user feedback by relevance feedback and attention fusion.
- 113
- Fast Approximate $$K$$-Means via Cluster Closures109
Using complexity analysis, real data clustering, and applications to image retrieval, this approach out-performs state-of-the-art approximate k-means algorithms in terms of clustering quality and efficiency.
- 106
- Tag refinement by regularized LDA96
A novel graphical model, regularized Latent Dirichlet Allocation (rLDA), is presented, which facilitates the topic modeling by exploiting both the statistics of tags and visual affinities of images in the corpus.
- 94
- SocialTransfer94
This paper investigates how to build a mutual connection among the disparate social media on the Internet, using which cross- domain media recommendation can be realized through SocialTransfer, a novel cross-domain real-time transfer learning framework.
- Distributed multi-view video coding92
A practical framework of distributed multi-view video coding, in which inter-camera communication is avoided and the large computing complexity is moved from encoder to decoder, and the traditional inter frame is replaced by Wyner-Ziv frame.
- Accelerate video decoding with generic GPU91
A video decoding framework that involves both the central processing unit (CPU) and the GPU is proposed and initial experimental results show that significant speed-up can be achieved by utilizing the GPU power.
- Probabilistic sequential POIs recommendation via check-in data89
A probabilistic recommendation approach is presented, which is highly motivated from a large-scale commercial mobile check-in data analysis, to ranking a list of sequential POI categories and POIs and enables users to plan consecutive activities on the move.
- 89
- 87
- Query-driven iterated neighborhood graph search for large scale indexing83
This paper presents a criterion to check if the local search over a neighborhood graph arrives at the local solution, and follows the iterated local search (ILS) strategy, widely-used in combinatorial optimization, to find a solution beyond a local optimum.
- Distributed prefetching scheme for random seek support in peer-to-peer streaming applications83
This work extracts a user viewing pattern that indicates that random seek is a pervasive phenomenon, contrary to the common assumptions that users would watch a video session sequentially and passively in most works on peer-to-peer streaming, and proposes an optimal prefetching scheduling algorithm based on the optimal scalar quantization theory.
- An Error Concealment Algorithm for Entire Frame Loss in Video Transmission82
This work proposes a bi-directional temporal error concealment method that can recover a whole missing frame and is efficient in stopping error propagation.
- Video search re-ranking via multi-graph propagation81
Experimental results verify the effectiveness of the graph-based propagation approach combined with the object-sensitive query analysis approach, which brings significant improvement to the baseline of text-based video search.
- Finding perfect rendezvous on the go79
This paper presents a novel approach to mobile visual localization that accurately senses geographic scene context according to the current image (typically associated with a rough GPS position) and showcases three novel applications: accurate self-localization, collaborative localization for rendezvous routing, and 3) routing for photographing.
- 74
- Lifting-based Wavelet Transform with Directionally Spatial Prediction73
The proposed DSP-lifting scheme can significantly outperform JPEG 2000 in terms of PSNR (up to 2dB) and visual quality and investigate the techniques to efficiently estimate and code the directional data, thus increasing the precision of spatial prediction and reducing the overhead bits.
- 72
- 72
- 68
- Contextual in-image advertising67
An innovative contextual advertising system driven by images is proposed, which automatically associates relevant ads with an image rather than the entire text in a Web page and seamlessly inserts the ads in the nonintrusive areas within each individual image.
- Memory-constrained 3D wavelet transform for video coding without boundary effects66
This paper proposes a memory-efficient transform technique via lifting that effectively computes wavelet transforms of a video sequence continuously on the fly, thus eliminating the boundary effects due to limited length of individual GOPs.
- Modeling social strength in social media community via kernel-based learning65
A kernel-based learning to rank framework for inferring the social strength of Flickr users, which involves two learning stages and is able to conduct collaborative recommendation and collective classification.
- When recommendation meets mobile65
An approach to context-aware and personalized entity recommendation which understands the implicit intent without any explicit user input on the phone, and deploys a recommendation application based on the proposed approach on Window Phone 7 devices.
- Encryption and authentication for scalable multimedia: current state of the art and challenges65
The general requirements and desirable features for an encryption or authentication system for scalable media, esp. those not encountered with the non-scalable case are described and an overview of the current state of the art of technologies in scalable encryption and authentication is presented.
- 60
- 60
- The role of attractiveness in web image search58
Experimental results on three large-scale web image search datasets demonstrate that the incorporation of attractiveness can bring more satisfaction to 80% of the users for ranking/reranking search results and 30.5% index coverage improvement for index selection, compared to the conventional relevance based approaches.
- Image search by concept map57
A new image search interface is proposed to enable users to formulate a query, called concept map, by intuitively typing textual queries in a blank canvas to indicate the desired spatial positions of the concepts.
- 57
- 57
- 55
- 55
- Million-scale near-duplicate video retrieval system53
A visual word based approach is proposed, which quantizes each video frame into a word and represents the whole video as a bag of words and can respond to a query in 41ms with 78.4% MAP on average.
- 53
- 53
- 53
- 52
- Advanced motion threading for 3D wavelet video coding52
An advanced motion threading technique is devised, in which one set of motion vectors is generated for each temporal layer of wavelet coefficients for temporal scalability, in order to reduce the motion overhead information, especially at low bit rates.
- 50
- 50
- Automatic video annotation by semi-supervised learning with kernel density estimation50
This paper proposes a novel semi-supervised learning algorithm, named Semi Supervised Learning by Kernel Density Estimation (SSLKDE), which is based on a non-parametric method, and therefore the "model assumption" is avoided.
- 50
- 49
- VideoReach49
This paper presents a novel online video recommendation system called VideoReach, which alleviates users' efforts on finding the most relevant videos according to current viewings without a sufficient collection of user profiles as required in traditional recommenders.
- Annotation for free48
It is shown that annotation can be performed for free with competitive performance and minimum computing resource, representing a new and promising paradigm for video tagging in addition to machine learning and data-driven methodologies.
- 46
- 45
- 44
- Barbell lifting wavelet transform for highly scalable video coding42
Replacing the conventional lifting with the proposed Barbell lifting, the 3D wavelet coding scheme achieves a high coding efficiency and guarantees the perfect reconstruction in various Barbell functions even with fractional precision.
- 40
- Exploiting temporal correlation with adaptive block-size motion alignment for 3D wavelet coding40
An adaptive block-size motion alignment technique in 3D wavelet coding to further exploit temporal correlations across pictures and an overlapped block motion alignment is further proposed to cope with block boundaries and to suppress spatial high-frequency components.
- Fast Neighborhood Graph Search Using Cartesian Concatenation39
Experimental results on searching over large scale datasets (SIFT, GISTand HOG) show that the proposed new data structure for approximate nearest neighbor search outperforms state-of-the-art ANN search algorithms in terms of efficiency and accuracy.
- 39
- 39
- ImageSense37
A contextual advertising system driven by images is presented, which automatically associates relevant ads with an image rather than the entire text in a Web page and seamlessly inserts the ads in the nonintrusive areas within each individual image.
- 37
- 36
- 36
- 35
- Image tag refinement by regularized latent Dirichlet allocation34
This paper proposes to do tag refinement from the angle of topic modeling and presents a novel graphical model, regularized latent Dirichlet allocation (rLDA), where tag similarity and tag relevance are jointly estimated in an iterative manner, so that they can benefit from each other.
- 34
- Advances in Multimedia Information Processing - PCM 2008: 9th Pacific Rim Conference on Multimedia, Tainan, Taiwan, December 9-13, 2008, Proceedings34
This book constitutes the refereed proceedings of the 9th Pacific Rim Conference on Multimedia, PCM 2008, held in Tainan, Taiwan, in December 2008, and contains 79 revised full papers and 39 revised poster presented.
- 33
- 33
- 33
- 31
- JIGSAW31
This paper presents an innovative application for mobile phone users to facilitate their visual search experience by taking advantage of smart phone functionalities such as multi-modal and multi-touch interactions, and demonstrates that it is an effective complement to existing mobile visual search applications.
- 31
- 31
- 30
- 30
- 30
- 30
- 29
- VideoSense29
VideoSense is able to detect a set of candidate ad insertion points based on content analysis, select a list of relevant candidate ads ranked according to textual relevance, and find the best match between insertion points and ads which maximizes the overall multimodal relevance.
- Advanced lifting-based motion-threading (MT) technique for 3D wavelet video coding28
The original motion-threading technique is extended to the lifting wavelet structure, which solves the artificial motion thread truncation problem in long support temporal wavelet filtering, and enables the accuracy of motion alignment to be fractional-pixel with guaranteed perfect reconstruction.
- QoS scheme for multimedia multicast communications over wireless mesh networks27
A quality of service (QoS) scheme for multimedia multicast communications in wireless mesh networks (WMNs) is proposed in this study that uses a new bandwidth calculation scheme to provide rate-adaptive admission control and operates independently of the media access control (MAC) layer.
- Efficient and Syntax-Compliant JPEG 2000 Encryption Preserving Original Fine Granularity of Scalability27
A novel syntax-compliant encryption primitive and an efficient syntax- Compliant JPEG 2000 encryption scheme that is fast, error-resilient, and has negligible file-size overhead are presented.
- 27
- Error-Resilient Unequal Error Protection of Fine Granularity Scalable Video Bitstreams26
This paper develops an error-resilient unequal error protection (ER-UEP) method that adds redundant information optimally for loss protection and cancels completely the dependency among bitstream after loss recovery and presents an algorithm that can optimally allocate the rate budget between data packets and parity packets.
- 26
- Symmetrical Multilevel Diversity Coding and Subset Entropy Inequalities25
The optimality of superposition coding is extended to the cases where there is either an additional all-access encoder or an additional secrecy constraint, and a subset entropy inequality recently proved by Madiman and Tetali is used to develop a new structural understanding of the work of Yeung and Zhang.
- 25
- 25
- 25
- 23
- Hybrid image summarization23
A novel approach, called Homogeneous and Heterogeneous Message Propagation (H2MP), which extends affinity propagation that only works over homogeneous relations to heterogeneous relations and the summary obtained by this approach is both visually and semantically satisfactory.
- Real-time video coding under power constraint based on H.264 codec23
A joint power-distortion optimization scheme for real-time H.264 video encoding under the power constraint is translated to the complexity constraint based on DVS technology and a computation allocation model with virtual buffers is proposed to facilitate the optimal allocation of constrained computational resource for each frame.
- Interactive image search by 2D semantic map22
A novel interactive image search system, image search by 2D semantic map, that enables users to indicate what semantic concepts are expected to appear and even how these concepts are spatially distributed in the desired images is presented.
- A comprehensive human computation framework22
The proposed schemes can successfully remove spurious answers from bots and distill human answers to produce high-quality image labels and indicate that the Web 2.0 approach to labeling images and videos efficiently is adopted.
- 22
- LazyCut22
LazyCut provides a semi-automatic video authoring and sharing system that significantly reduces users' efforts in video editing while preserving sufficient flexibility and personalization.
- 22
- 22
- 22
- 21
- Scalable portrait video for mobile video communication21
The generation, coding, and transmission of an effective video form, scalable portrait video for mobile video communication, and the first to enable two-way video communication on pocket PCs and handheld PCs are described.
- 19
- Optimized Distances for Binary Code Ranking19
Extensive experimental results show superior performance of the proposed approach over state-of-the-art methods on three real-world high-dimensional datasets for binary code ranking.
- 19
- 19
- Optimal subband rate allocation for spatial scalability in 3D wavelet video coding with motion aligned temporal filtering19
An error propagation model is proposed to describe the effect of subband coupling in video reconstruction and the synthesis gain of each subband is estimated according to this model and it is finally adopted to guide the rate allocation algorithm.
- Studies on spatial scalable frameworks for motion aligned 3D wavelet video coding19
A novel non-redundant multi-T+2D framework has a good performance for fully scalable video coding and is practical in providing narrow range SNR scalability for each spatial layer.
- 18
- 18
- 18
- A proxy-based mobile web browser18
This paper uses the server-side web parsing and rendering to leverage the browser computing logic and uses a composite screen format to represent the display of the web content, incorporating the web background screen and the dynamic web objects.
- Optimized streaming media proxy and its applications18
By validating the implementation of the optimized streaming proxy system, the experimental results show that the streaming proxy can effectively contribute to reduce the server and backbone network load, thus achieve improved media quality and scalability.
- 17
- 17
- 17
- 16
- 16
- 16
- 16
- Browse-to-Search15
This work develops a novel system to explore an effective and efficient way for allowing users to seamlessly switch between browse and search processes, and naturally complete visual-based exploratory search tasks, and provides users with more robust results to satisfy their exploring experience.
- 15
- Listen, look, and gotcha15
An innovative instant mobile video search system through which users can discover videos by simply pointing their phones at a screen to capture a very few seconds of what they are watching through which the system outperforms state-of-the-art methods.
- Contextual image search15
The key idea is to use the search-to-annotation technique and the contextual textual query mining scheme to determine the corresponding textual query, to finally get semantically similar search results.
- Interactive video authoring and sharing based on two-layer templates15
LazyMedia provides a semiautomatic video authoring and sharing system that significantly reduces users' efforts in video editing while preserving sufficient flexibility and personalization.
- Free viewpoint switching in multi-view video streaming using Wyner-Ziv video coding15
A novel free viewpoint switching scheme for multi-view video scenario, in which the distributed video coding technique is employed, and the inter-camera communication can be avoided and the drifting error can be controlled efficiently when the viewpoint switching occurs.
- Energy distributed update steps(edu) in lifting based motion compensated video coding15
A new update scheme, energy distributed update steps (EDU), is proposed for the temporal transform in lifting based motion compensated video coding to update where predict is made by distributing high-pass signals to the low-pass frame.
- Personal media sharing and authoring on the web15
Three primary technologies enable this end-to-end system, including scalable video coding, intelligent multimedia content analysis, and template-based media authoring, which reduces the workload of media sharing and authoring.
- Efficient Comb Elliptic Curve Multiplication Methods Resistant to Power Analysis15
This paper presents a novel comb recoding algorithm which converts an integer to a sequence of signed, odd-only comb bit-columns and presents several comb methods, both Simple Power Analysis (SPA)-nonresistant and SPA-resistant, for point multiplication which are resistant to all power-analysis attacks.
- PLI: A New Framework to Protect Digital Content for P2P Networks15
A novel Public License Infrastructure that uses cryptographic threshold secret sharing schemes to provide decentralized public license services for the Digital Rights Management (DRM) and proposes a PLI-based DRM system to provide content protection and digital rights management for users of Peer-to-Peer networks.
- Drifting reduction in progressive fine granularity scalable video coding15
The experimental results show that the PFGS scheme incorporating the proposed technique can effectively reduce the drifting errors at low bit rates and improves the coding efficiency up to 1.8dB compared with the FGS scheme at moderate or high bit rates.
- Error Resilience Methods for FGS Video Enhancement Bitstream15
The experimental results show that the proposed hierarchical enhancement layer bitstream has stronger error detection and resynchronization capabilities when transmitted over error-prone channels and provides much better decoded video.
- 14
- 14
- Detection of salient objects with focused attention based on spatial and temporal coherence14
The effectiveness and complementariness of the two types of coherence are shown, and they can significantly improve the performance of salient object detection in videos, and are demonstrated to be robust to unexpected environment changes and camera vibrations.
- Spatial Scalability in 3D Wavelet Coding with Spatial Domain MCTF Encoder14
To completely address the spatial scalability issues in spatial-domain MCTF schemes, optimization of bit allocation is needed to reasonably allocate part of the bandwidth to spatial high-frequency coefficients, instead of dropping them completely.
- 14
- 14
- 14
- 14
- 14
- 13
- Generalized cut-set bounds for broadcast networks13
A new set of explicit network coding bounds, which combine different simple cuts of the network via a variety of set operations (not just the union), are established via their connections to extremal inequalities for submodular functions.
- A bag-of-objects retrieval model for web image search13
This paper proposes a novel bag-of-objects retrieval model for image search reranking of object queries that can significantly outperform the existing reranking methods on object queries.
- 13
- Signed MSB-Set Comb Method for Elliptic Curve Point Multiplication13
An efficient comb method and its Simple Power Analysis (SPA)-resistant counterpart are presented and it is concluded that these comb methods are among the most efficient comb methods in terms of number of precomputed points and computational complexity.
- 13
- 13
- 13
- 13
- 13
- A video coding algorithm using vector-based techniques13
Coding results have shown that a gain in peak signal-to-noise ratio (PSNR) up to 8 dB for intraframe coding and up to 6 dB for interframe coding can be achieved over H.263.
- 12
- 12
- ThresPassport – A Distributed Single Sign-On Service12
ThresPassport (Threshold scheme-based Passport), a web-based, distributed Single Sign-On (SSO) system which utilizes a threshold-based secret sharing scheme to split a service provider's authentication key into partial shares distributed to authentication servers.
- 12
- Shape-adaptive discrete wavelet transform for coding arbitrarily shaped texture12
The proposed shape adaptive discrete wavelet transform (SA-DWT) scheme for coding arbitrarily shaped texture coding is presented and the small energy increase is restricted at the boundary of objects in subbands.
- A High-Fidelity and Low-Interaction-Delay Screen Sharing System11
A layered structure for screen coding and rendering is proposed to deliver diverse screen content to the client side with an adaptive frame rate to enable screen sharing among multiple devices with high fidelity and responsive interaction.
- Robust and accurate mobile visual localization and its applications11
A novel approach to mobile visual localization according to a given image (typically associated with a rough GPS position) is presented, capable of providing a complete set of more accurate parameters about the scene geo-context including the real locations of both the mobile user and perhaps more importantly the captured scene, as well as the viewing direction.
- Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving10
GLM decomposes reasoning into specialized agents for classification, reasoning, action generation, and graph retrieval, enabling branching and selective context sharing to reduce prompt length and reasoning iterations while preserving reasoning quality, thereby improving accuracy and reducing overall token consumption.
- MR Image Harmonization with Transformer10
The proposed Transformer-based MR image harmonization method leverages the self-attention mechanism of the Transformer to learn the complex relationships between image patches and effectively transfer the imaging characteristics from a source image domain to a target image domain.
- 10
- Color filter for image search10
A color filter scheme for image search is shown, which enables users to find images containing objects or scenes with their interested color, one of the most crucial cues in describing visual contents.
- Local visual words coding for low bit rate mobile visual search10
A third scheme for extremely low bit rate mobile visual search is proposed, which sends compressed visual words consisting of vocabulary tree histogram and descriptor orientations rather than descriptors, and obtains about 30% improvement over the traditional Bag-of-Words baseline.
- Interactive mobile visual search for social activities completion using query image contextual model10
- Accelerometer-based single-handed video browsing on mobile devices10
Evaluation on a group study indicates that this new design provides a natural user experience for single-handed video navigation, and therefore an effective complement to existing video browsing mechanisms on mobile devices.
- 10
- 10
- 10
- 10
- Direct macroblock coding for predictive (P) pictures in the H.264 standard10
A new Inter Macroblock type within the H.264 video coding standard is introduced that can further improve coding efficiency by exploiting the temporal correlation of motion within a sequence, while retaining or even improving quality under a Rate Distortion Optimization Framework.
- 10
- 9
- Adaptive energy management strategy for plug-in hybrid electric vehicles based on intelligent recognition of driving cycle9
Simulation results show that compared with ECMS strategy, A-ECMS strategy can maintain high fuel economy under complex driving cycles, and improve the vehicle's fuel economy up to 3%.
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- Three-dimensional shape-adaptive discrete wavelet transforms for efficient object-based video coding9
An object-based coding scheme using 3D shape-adaptive discrete wavelet transforms (SA- DWT) using a 3D entropy coding algorithm called Motion-based Embedded Subband Coding with Optimized Truncation (ESCOT) to code the wavelet coefficients.
- Automatic salient object sequence rebuilding for video segment analysis8
This study reformulated the problem as a binary labeling problem, analyzed the potential salient object sequences in the video using a clustering method, and separated the salient object sequence from the background by applying an energy optimization method.
- TapTell: Interactive visual search for mobile task recommendation8
This paper develops TapTell, an exemplary real application on Windows Phone seven, by taking advantages of user interaction and rich context to enable interactive visual searches and contextual recommendations, and compared the results to state-of-the-art algorithms for image retrieval.
- 8
- 8
- 8
- 8
- 8
- 8
- LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment7
A novel gradient-alignment-based method, named LearnAlign, which intelligently selects the learnable and representative training reasoning data for RLVR post-training, and introduces the data learnability based on the success rate, which indicates the learning potential of each data point.
- 7
- A series of molecular modeling techniques to reveal selective mechanisms of inhibitors to β-Site amyloid precursor protein cleaving enzyme 1 (BACE1) and β-site amyloid precursor protein cleaving enzyme 2 (BACE2)7
The physical principles revealed by this study may facilitate the rational design of more potent BACE1 selective inhibitors.
- An Indoor Positioning Method Based on RSSI Probability Distribution7
This paper proposes to use the probability distribution of RSSI value as a fingerprint feature over a period of time, and combines the dimension reduction algorithm and the weighted K nearest neighbor algorithm to achieve positioning.
- 7
- Salable Image Search with Reliable Binary Code7
This paper investigates the reliability of each bit in scalar quantization and proposes a novel reliable binary SIFT feature that accelerates the search speed by narrowing search space, but also improves the retrieval accuracy by alleviating the impact of unreliable quantized bits.
- Depth sensor assisted real-time gesture recognition for interactive presentation7
A gesture recognition approach to enable real-time manipulating projection content through detecting and recognizing speakers gestures from the depth maps captured by a depth sensor is presented.
- Scalable similar image search by joint indices7
This work presents an efficient and effective indexing algorithm, neighborhood graph index, which is suitable for millions of images, and uses it to organize joint inverted indices to search over billions of images.
- Video-based image retrieval7
A novel QBE-based image retrieval system where users are allowed to submit a short video clip as a query to improve the retrieval reliability and improve the relevance of the retrieved results is proposed.
- 7
- New attacks on SARI image authentication system7
Two new attacks that can compromise the SARI system, called histogram attack and oracle attack, which uses an oracle to efficiently find the secret pairs used by SARI in its signature generation are proposed.
- 7
- 7
- Hybrid Single Input and Multiple Output Method For Compressing Features Towards Machine Vision Tasks6
- 6
- 6
- 6
- 6
- 6
- Generalized in-scale motion compensation framework for spatial scalable video coding6
Preliminary experimental results demonstrate that the proposed framework improves the spatial scalability performance of current H.264/MPEG-4 SVC, and another advantage over wavelet-based in-scale scheme is achieved that it can support arbitrary down-sampled and up-sampling filters.
- Scalable Video Coding for Adaptive Streaming Applications6
This chapter discusses the scalable video coding for adaptive streaming applications, which addresses both the video coding and the networking challenges associated with IP-based video streaming is scalability.
- Drift-free switching of compressed video bitstreams at predictive frames6
Two schemes are proposed to efficiently compress video contents into bitstreams that support drift-free switching at predictive frames and an empirical method is proposed to achieve a good tradeoff between high coding efficiency of SP frames and small size of switching bits.
- Compression with vision technologies6
A method for image compression in which currently developed vision technologies are incorporated with traditional transform-based coding methods, and two coding-oriented inpainting methods are presented: structure-aware in painting and object-based inPainting.
- 6
- 6
- To mine capture intention of camcorder users6
This approach models the capture intention from a camcorder user's point of view, by investigating a set of effective intention oriented features, and concludes that the intention based approach is an effective complement to existing home video content analysis schemes.
- 6
- A Peer-to-Peer Communication System6
In the system, in addition to being aware of each other's presence, users can simultaneously attend multiple multimedia meetings with each meeting allowing multiple attendees, and have full control over the exchange of real-time text/voice/video information in these meetings.
- 6
- 6
- On boundary effects in 3-D wavelet video coding6
A memory efficient transform technique via lifting that effectively computes wavelet transforms of a video sequence continuously on the fly, thus eliminating the boundary effects due to limited length of individual GOPs.
- 5
- 5
- When video search goes wrong5
This work proposes a novel approach for predicting a failure of a video search query in the specific context of a search session, using a combination of 'user indicators' and 'engine indicators' to predict whether a particular query is likely to fail in thecontext of a particular search session.
- ReDi5
Evaluations show that the proposed system can efficiently utilize the remote computing resources and local display capabilities of ubiquitous devices, which will greatly benefit interactive multimedia applications.
- Rate-distortion optimized color quantization for compound image compression5
A rate-distortion optimized color quantization algorithm for text/graphic content, which introduces distortion to text content and minimizes the bit rate produced by the following lossless entropy compression algorithm.
- 5
- HALF-PIXEL MOTION ESTIMATION BYPASS BASED ON A LINEAR MODEL5
A novel half-pixel motion estimation bypass algorithm based on a linear model that is very suitable for scenarios where lowcomplexity computing is required, such as mobile video coding applications.
- 5
- 5
- New vector transform for image coding5
A general rate- distortion formula for signal processing combined with vector quantization for first-order Gaussian-Markov source is obtained and it is proved that VTC indeed has better performance than other existing coding schemes with the same or less complexity based on the rate-distortion measurement.
- Echo: Efficient Co-Scheduling of Hybrid Online-Offline Tasks for Large Language Model Serving4
Echo, a collaborative online-offline task serving system, including a scheduler, a KV cache manager, and estimation toolkits is introduced, which can increase offline task throughput by up to $3.3\times, while satisfying online task SLOs.
- 4
- R-D optimal motion estimation for fast H.264/AVC bit-rate reduction4
Experimental results show that the proposed RD model can improve the coding efficiency about 5 dB with similar speed, compared with the motion reuse transcoder, and significantly reduces the transcoding complexity.
- 4
- Contextual In-Stream Video Advertising4
This chapter presents a new advertising paradigm for online video, called contextual in-stream video advertising, which automatically associates the most relevant video ads with online videos and seamlessly inserts the ads at the most appropriate spatiotemporal positions within each individual video.
- 4
- 4
- 4
- 4
- Segment tree based control plane protocol for peer-to-peer on-demand streaming service discovery4
This paper fully decouple the control plane and data plane in video streaming, and hence provide more flexibilities in designing protocols on both of them.
- Transcoding for progressive fine granularity scalable vide coding4
Experimental results show that the transcoding scheme proposed here is to improve the coding performance of scalable video signals when bandwidth has large change.
- 4
- 4
- 4
- Multimetric evaluation protocol for user-assisted video object extraction systems4
A multi-metric evaluation protocol is proposed, including metrics for contour-based spatial matching, temporal consistency, user workload and time consumption, inspired by a novel framework for performance evaluation on image segmentation using Pareto front.
- 4
- 4
- Efficient video coding with hybrid spatial and fine-grain SNR scalabilities4
In order to improve the coding efficiency and reduce the drifting errors at the high-resolution enhancement layer, five macroblock coding modes with different forms of motion compensation and reconstruction, are proposed in this paper.
- 3
- Paradigm Shifts in Video Technologies: Introduction to T-CSVT Future Special Issues3
New trends ranging from breakthroughs in information theory and machine learning, big data, crowd sourcing, cloud computing, low-cost yet powerful computing end points, Internet of things (IoT), mobile and wireless computing, augmented reality, green computing, to integrated system research are observed.
- Searching for images by video3
A framework in which the problem of reliability of QBE-based image retrieval is explicitly addressed and the rich information contained therein can be exploited to discover the proper query representation and to improve the relevance of the retrieved results is proposed.
- 3
- 3
- 3
- A Novel Privacy and Copyright Protection Enforced Peer-to-Peer Network3
A novel and practical P2P network with a strong privacy protection and reliable tracking mechanism to track the original uploader of any material in the P 2P network is proposed.
- 3
- 3
- 3
- 3
- 3
- Motion vector prediction with reference frame consideration3
A new motion vector prediction method that could be used within multiple picture reference codecs, such as the H.264 (MPEG-4 AVC) video coding standard, that considers for each candidate motion vector the temporal distance of its corresponding reference picture compared to the current one for the generation of the predictor motion vector.
- 3
- 3
- 2
- Feature-Aware Noise Contrastive Learning For Unsupervised Red Panda Re-Identification2
A Feature-Aware Noise Contrastive Learning method to explore an unsupervised learning solution, which is then validated on the task of red panda re-ID, and outperforms several related state-of-the-art unsupervised methods, achieving high performance comparable to supervised learning methods.
- 2
- 2
- 2
- A curvature-based weighted fuzzy c-means algorithm for point clouds de-noising2
The experimental results show that this approach is efficient to different scale and intensities of noise in point cloud with a high precision, and perform a feature-preserving nature at the same time, and robust enough to different noise model.
- 2
- 2
- 2
- 2
- 2
- Advances in Multimedia Modeling2
This talk covers perspectives on adaptive video streaming and how such techniques are essential for systems with heterogeneous devices and mechanisms that use Quality of Experience (QoE) metrics to enhance its performance for the users will be shown.
- 2
- 2
- 2
- Visual Communications and Image Processing 20052
Original and unpublished material of novel techniques and new developments are solicited on the following and related topics: visual communication.
- An extension of direct macroblock coding in Predictive (P) slices of the H.264 standard2
This paper introduces additional methods into H.264 that further enhance motion compensation and can lead to additional improvements in coding efficiency by further exploiting motion vector temporal correlation through the introduction of a new DIRECT macroblock type and an enhancement to the existing Skip Macroblock type within Predictive (P) slices.
- 2
- Flexible p-picture (FLEXP) coding for tue efficient fine-granular scalabilitv (FGS)2
The proposed FlexP technique provides more flexibility on bandwidth adaptation, as well as achieves a good trade-off between high coding efficiency and low drifting error at the enhancement layer especially when the R-D rate allocation is enabled.
- 2
- 2
- 2
- A motion compensated lifting wavelet codec for 3D video coding2
A motion compensated lifting (MCLIFT) framework for the 3D wavelet video coding is proposed in this paper, using bi-directional motion compensation in each lifting step of the temporal direction to ensure scalable video coding at frame rate and quality level.
- 2
- 2
- Flexible and Efficient Switching Techniques between Scalable Video Bitstreams2
Experimental results show that the seamless switching scheme with the proposed switching techniques significantly outperforms both the approach with a single scalable bitstream and the approach of switching among multiple nonscalable bitstreams.
- 2
- 2
- 2
- 1
- Neighborhood relation-based incremental label propagation algorithm for partially labeled hybrid data1
A novel incremental label propagation algorithm based on neighborhood relation (ILPN) is developed and extensive experiments validate that the proposed algorithm LPN can outperform other label propagation algorithms in speed on the premise of ensuring accuracy.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Research on Indoor Positioning Method Based on Improved HS-AlexNet Model1
An advanced AlexNet network model combined with Harris feature detection is put forward, which guides the image processing of the original model according to the detected Harris characteristics, it reduces the randomness error and improves the generalization ability and robustness of the model.
- New results on multilevel diversity coding with secure regeneration1
It is shown that the MBR point of the achievable normalized storage-capacity repair-bandwidth tradeoff region remains the same even if the eavesdropper can access the repair data for some compromised storage nodes but only the data contents of the remaining compromised nodes.
- Editor-in-Chief Message: Embracing the Era of Intelligent Visual Technology and Systems1
It is such a great honor and pleasure for me to assume the role of Editor-in-Chief of IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), starting in January 2018.
- 1
- Monitoring of Multimode Processes Based on Quality‐Related Common Subspace Separation1
A new monitoring approach for multimode processes based on quality-related common subspace separation is proposed, and the simulation results show the proposed method is effective.
- Content adaptive screen image scaling1
This paper proposes an efficient content adaptive screen image scaling scheme for the real-time screen applications like remote desktop and screen sharing that can achieve good visual quality and also keep the low complexity for realtime applications.
- 1
- Query-driven iterated neighborhood graph search for scalable visual indexing1
This paper investigates a simple but very effective approach, neighborhood graph (NG) search, which conducts the local search by expanding neighborhoods with a best-first manner, and proposes a query-driven iterated neighborhood graph search approach to improve the performance.
- 1
- 1
- 1
- TapTell1
This demonstration presents a mobile-based visual recognition and recommendation application on Windows Phone 7 called TapTell, which discovers and understands users' visual intents via a circle based natural user interaction called "O" gestures and recommends relevant entities utilizing contextual information.
- The Trends in multimedia computing1
The common features of the new wave of multimedia applications which I call Media 2.0 are summarized and 6 D's are described, namely, Democratized media life cycle; Data-driven media value chain; Decoupled media system; Decomposed media contents; Diminished media boundary between physical and virtual world; and Decentralized media business model.
- 1
- 1
- 1
- 1
- ImageSense1
This demonstration presents an innovative contextual advertising platform for online image service, called ImageSense, which aims to embed more contextually relevant ads at less intrusive positions within each suitable image.
- 1
- 1
- Scalable Wyner-Ziv video coding with adaptive bit-plane representation1
A simplified adaptive bit-plane representation is proposed without pre-knowing the Laplacian distribution parameters for the DCT-domain Wyner-Ziv video coding, in which the encoding can stop at any bit-planes and the bit-stream can also be flexibly truncated.
- 1
- 1
- 1
- Scalable Protection for MPEG-41
Two novel encryption algorithms for MPEG-4 FGS are proposed that are fast, error-resilient, and have negligible compression overhead and can be applied to other scalable multimedia formats.
- 1
- 1
- 1
- 1
- Image and Video Coding1
An overview of some basic concepts, principles, techniques, and standards in this research area of image and video coding is provided.
- 1
- 1
- Bitstream switching for progressive fine granularity scalable video coding1
Compared with other bitstream switching schemes, the proposed scheme shows its flexibilities and various advantages due to using the common base layer, and can significantly improve the streaming performance of the scalable bitstreams.
- 1
- –
- –
- –
- –
- –
- –
- A civil unmanned aircraft intelligent control system based on multisource sensor–
A civil UAV intelligent operation and maintenance system based on multi-source sensor data, which realizes real-time flight status and flight data monitoring and reality of UAVs by integrating LiDAR, vision system and other sensors, which can automatically enter the hangar for charging and maintenance according to the instruction.
- –
- –
- –
- Research on Distributed Calculation of Flight Parameters Based on Hadoop–
The results show that the parallel calculation of flight parameters based on Hadoop could save time used by 51% with the consistency of calculation results, which is the same as the standalone deployment.
- Research on Modeling Method of Massive Launch Vehicle Time Series Data–
The performance simulation results show that the storage method based on time series database has the best performance, and meets the storage requirements of massive time series data in the future for launch vehicles.
- –
- –
- Editor-in-Chief Message–
It is confirmed that the Editor-in-Chief of the IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) will retire at the end of this year, and the TCSVT will be in the capable hands of the new EiC, Prof Feng Wu from the University of Science and Technology of China.
- –
- A Bayesian Network Approach to Launch Vehicle Software Failure Prediction–
In this paper, a Markov Bayesian Network model for Launch Vehicle software failure prediction (MBNG) is proposed and unique features of Launch vehicle software is considered as an important part in the modeling process, which improves the effectiveness of this novel model.
- Indoor scene classification of robot vision based on cloud computing–
Experimental results show that the proposed algorithm can attain better real-time performance and is 1.4∼2.1 times faster than traditional classification methods which rely on single computation, while keeping stable classification correct rate as 70%.
- Nonlinear Diversified Processes Monitoring–
The paper proposed a new method to classify and establish the monitoring model for diversified processes data with multiscale that makes the correlation between the common subspace itself and input-output dataset of each mode as close as possible.
- –
- –
- –
- Advances in Multimedia Modeling: 19th International Conference, MMM 2013, Huangshan, China, January 7-9, 2013, Proceedings, Part I–
This talk covers perspectives on adaptive video streaming and how such techniques are essential for systems with heterogeneous devices and mechanisms that use Quality of Experience (QoE) metrics to enhance its performance for the users will be shown.
- –
- –
- –
- Peer-Paired collaboration for on-demand streaming applications and an improved error recovery technique–
A peer-paired collaborative streaming architecture is applied that exploits the power of peer-to-peer networking and extends the peer-PAired collaboration from a live broadcasting scenario to the more general on-demand streaming scenario by introducing a unique catch-up scheme.
- Radar Waveform Design for Low Power Monostatic Backscattering Ionosonde–
The waveform can achieve high pulse compression gain, long unambiguous range, highrange resolution and high Doppler resolution, and are specially suitable for low power monostatic backscattering ionosonde.
- –
- Media 2.0 – The New Media Revolution?–
The common features of the new wave of multimedia applications which I call Media 2.0 are summarized and 5 D's are described to describe Media 1.0 principles, namely, Democratized media life cycle; Data-driven media value chain; Decoupled media system; Decomposed media contents; and Decentralized media business model.
- –
- –
- IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY Editor-in-Chief–
This special issue, which focuses on event analysis in broad problem domains, has witnessed the effectiveness of using both static and temporal information in event recognition from other video sources.
- Subband Coupling Aware Rate Allocation for Spatial–
This paper first analyzes the signal coupling phenomenon and then proposes a quantitative model to describe signal propagation across spatial subbands during the MCTF process, called subband coupling aware signal propagation (SCASP) model.
- –
- File format for storage of scalable video–
The file format for scalable video is proposed based on ISO Base Media File Format, which is simple and flexible enough to address the demands of scalable video application as well as the non-scalable ones.
- Segment Tree Based Control Plane Protocol for Peer-to-Peer Streaming Service Discovery–
This paper fully decouple the control plane and data plane on video streaming, and hence provide more flexibilities in designing protocols on both of them.
- –
- –
- –
- –
- –
- –
- Low Bitrate Watercolor Video–
A low bitrate watercolor-like video form, which is constructed with a bi-level Y luminance component and a number of UV chrominance combinations and the resultant video looks better than bi- level video and its bitrate is still lower than that of full-color video.
- Boundary effects in 3D wavelet video coding–
A memory efficient transform technique via lifting that effectively computes wavelet transforms of a video sequence continuously on the fly, thus eliminating the boundary effects due to limited length of individual GOPs.
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 2026-10-15. 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.