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
- Changsheng XuSuggested from co-authorship
- Qi Chuan TianSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works227 from public data
- NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding1,846
This work introduces a large-scale dataset for RGB+D human action recognition, which is collected from 106 distinct subjects and contains more than 114 thousand video samples and 8 million frames, and investigates a novel one-shot 3D activity recognition problem on this dataset.
- 704
- Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning452
A data-free knowledge distillation method to fine-tune the global model in the server (FedFTG), which relieves the issue of direct model aggregation and develops customized label sampling and class-level ensemble to derive maximum utilization of knowledge.
- Classes Matter: A Fine-Grained Adversarial Approach to Cross-Domain Semantic Segmentation346
This work proposes a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains, which outperforms other global feature alignment based and class-wise alignment based counterparts.
- Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics271
The definition, formulation, and paradigm of VCM are given, and the preliminary results have demonstrated the performance and efficiency gains, and state-of-the-art techniques in video compression and feature compression are systematically reviewed from the unique perspective of MPEG standardization.
- 271
- 231
- 210
- 209
- Location Discriminative Vocabulary Coding for Mobile Landmark Search191
A Location Discriminative Vocabulary Coding (LDVC) scheme, which achieves extremely low bit rate query transmission, discriminative landmark description, as well as scalable descriptor delivery in a unified framework is presented.
- A mid-level representation framework for semantic sports video analysis190
A generic mid-level representation framework is introduced between the low-level audio-visual processing and high-level semantic analysis and can be used for event detection, highlight extraction, summarization and personalization of many types of sports video.
- 182
- Generalizable Person Re-identification with Relevance-aware Mixture of Experts174
This work proposes a novel method called the relevance-aware mixture of experts (RaMoE), using an effective voting-based mixture mechanism to dynamically leverage source domains’ diverse characteristics to improve the model’s generalization.
- Skeleton-Based Online Action Prediction Using Scale Selection Network174
A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a sliding window over the temporal axis and a novel window scale selection method is proposed to make the network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step.
- IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID154
An Intermediate Domain Module (IDM) is proposed to generate intermediate domains’ representations on-the-fly by mixing the source and target domains�’ hidden representations using two domain factors and ensures two properties that these intermediate domains should satisfy.
- HMM-Based Audio Keyword Generation148
Experimental results show that, for audio keyword generation, the proposed HMM-based method outperforms the previous hierarchical SVM, and is motivated by the successful story of HMM in speech recognition.
- 145
- 142
- CRRN: Multi-scale Guided Concurrent Reflection Removal Network137
This paper proposes the Concurrent Reflection Removal Network (CRRN), a network that integrates image appearance information and multi-scale gradient information with human perception inspired loss function, and is trained on a new dataset with 3250 reflection images taken under diverse real-world scenes.
- 136
- Feature Boosting Network For 3D Pose Estimation135
A context consistency gate (CCG) is introduced in this paper, with which the convolutional feature maps are modulated according to their consistency with the context representations, to improve the reliability of the features for representing each body part and enhance the LSTD module.
- Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification114
This work proposes a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID.
- 106
- 105
- 103
- 100
- ChipGAN97
The advantages in visual quality compared with state-of-the-art networks and high stylization perceptual study scores show the effectiveness of the proposed ChipGAN, an end-to-end Generative Adversarial Network based architecture for photo to Chinese ink wash painting style transfer.
- Segmentation, categorization, and identification of commercial clips from TV streams using multimodal analysis94
A multimodal ("visual + audio + text") commercial video digest scheme to segment individual commercials and carry out semantic content analysis within a detected commercial segment from TV streams is presented.
- Fast and robust short video clip search using an index structure93
An index structure-based method to fast and robustly search short video clips in large video collections and develops a set of spatial-temporal features in order to globally capture the pattern of a short video clip and combine it with the color range feature to form video signatures.
- Compact Descriptors for Video Analysis: The Emerging MPEG Standard91
The new standard that is being developed and the performance of these key technical contributions are described are described.
- 91
- Market2Dish: Health-aware Food Recommendation89
A personalized health-aware food recommendation scheme, namely, Market2Dish, mapping the ingredients displayed in the market to the healthy dishes eaten at home and a novel category-aware hierarchical memory network–based recommender to learn thehealth-aware user-recipe interactions for better food recommendation is presented.
- 88
- 87
- Towards Coding For Human And Machine Vision: A Scalable Image Coding Approach86
Experimental results demonstrate the superiority of the novel image coding framework in both human visual quality and facial landmark detection, which provide useful evidence on the emerging standardization efforts on MPEG VCM (Video Coding for Machine).
- Towards Low Light Enhancement With RAW Images85
A RAW-guiding Exposure Enhancement Network (REENet), which makes trade-offs between the advantages and inaccessibility of RAW images in real applications in a way of using RAW images only in the training phase, and demonstrates not only the superiority of REENet to state-of-the-art sRGB-based methods and but also the effectiveness of the RAW guidance and all components.
- Lossy Intermediate Deep Learning Feature Compression and Evaluation82
This work proposes to compress and transmit intermediate deep learning features instead of visual signals and ultimately utilized features to enable a better balance among bandwidth usage, computational load and the generalization capability for cloud-end servers.
- 79
- FHDe2Net: Full High Definition Demoireing Network76
The proposed Full High Definition Demoir´eing Network (FHDe 2 Net) consists of a global to local cascaded removal branch to eradicate multi-scale moir´e patterns and a frequency based high-resolution content separation branch to retain details.
- Incorporating intra-class variance to fine-grained visual recognition73
The triplet loss function is strengthened by incorporating intra-class variance with GS-TRS, which may contribute to the optimization objective of triplet network.
- IDeRs: Iterative dehazing method for single remote sensing image71
An Iterative Dehazing for Remote Sensing image (IDeRS) is proposed, in which dehazing operator is implemented iteratively to remove haze progressively until arriving at a satisfied result, and a fusion model for combining patch-wise and pixel-wise dehazed operators to overcome both halos and over-saturation caused by them respectively.
- 70
- 69
- 62
- 62
- 62
- 62
- 61
- Towards low bit rate mobile visual search with multiple-channel coding55
Quantitative comparisons to the state-of-the-arts demonstrate the significant advantages in descriptor compactness and retrieval mAP in mobile landmark, product, and CD/book cover search.
- 53
- 51
- 50
- 49
- 48
- 48
- 47
- Benchmarking Single-Image Reflection Removal Algorithms46
This paper presents a SIngle-image Reflection Removal Plus dataset, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of-the-art (especially learning-based) methods.
- 46
- 45
- 43
- 41
- 40
- Attribute-wise Explainable Fashion Compatibility Modeling39
An attribute-wise explainable FCM solution, named ExFCM, which can simultaneously generate the item-level compatibility evaluation for input fashion items and the attribute-level explanations for the evaluation result, together with reasonable explanations.
- 39
- Face Image Reflection Removal38
The face image reflection removal problem is solved by incorporating inpainting ideas into a guided reflection removal framework, which takes two images as the input and considers various face-specific priors.
- 38
- Disentangled Feature Learning Network for Vehicle Re-Identification37
A Disentangled Feature Learning Network (DFLNet) is proposed to learn orientation specific and common features concurrently, which are discriminative at details and invariant to orientations, respectively.
- 37
- 36
- 35
- 33
- 33
- Fast and Robust Short Video Clip Search for Copy Detection33
This paper designs a novel global visual feature (a fixed-size 144-d signature) combining the spatial-temporal and the color range information and achieves an efficient and robust solution for video copy detection.
- An Emerging Coding Paradigm Vcm: A Scalable Coding Approach Beyond Feature And Signal32
This paper employs a conditional deep generation network to reconstruct video frames with the guidance of learned motion pattern via a predictive model, which elegantly leverages the feature representation to generate the appearance of to-be-coded frames via a generative model.
- From Part to Whole32
A multi-task multi-range (MTMR) representation framework is proposed which is composed of local, regional and global representations and attempts to optimize authorship identification with subtly correlated identification tasks such as style, genre and date.
- 32
- Automatic sports genre categorization and view-type classification over large-scale dataset32
A framework with two automatic tasks targeting large-scale and low quality sports video archives collected from online video streams based on the bag of visual-words model using speeded-up robust features (SURF).
- 31
- 30
- Semantic Shot Classification in Sports Video30
A unified framework for semantic shot classification in sports videos that makes use of domain knowledge of a specific sport to perform a top-down video shot classification, including identification of video shot classes for each sport, and supervised learning and classification of the given sports video with low-level and middle-level features extracted from the sports video.
- 29
- 29
- 29
- 28
- LSTM neural network for solar radio spectrum classification28
This paper makes the first attempt to utilize an RNN, specifically long short-termmemory (LSTM) for solar radio spectrum classification, and demonstrates that LSTM can learn a better representation of a spectrum, and thus contribute better classification.
- 27
- 26
- 25
- 25
- 25
- Market2Dish24
A word-class interaction based text classification model is employed to learn the fine-grained similarity between sparse health features on the social media platforms and pre-defined health concepts, and then a category-aware hierarchical memory network based recommender is introduced to learning the user-recipe interactions for better food recommendations.
- 23
- 23
- DeepHash for Image Instance Retrieval23
In-depth evaluation shows that the proposed DeepHash scheme outperforms state-of-the-art methods over several benchmark datasets for both Fisher Vectors and Deep Convolutional Neural Network features, by up to 8.5% over other schemes.
- 23
- 22
- 21
- Hamming compatible quantization for hashing21
This paper proposes a multi-bit quantization method named Hamming Compatible Quantization (HCQ) to preserve the capability of similarity metric between Euclidean space and Hamming space by utilizing the neighborhood structure of raw data.
- 20
- 20
- Bridging the Source-to-Target Gap for Cross-Domain Person Re-identification with Intermediate Domains19
This paper proposes an Intermediate Domain Module (IDM) and a Mirrors Generation Module (MGM), introduced to compensate the loss of the original identity by mapping the features into the IDM-generated intermediate domains without changing their original identity, which reinforces IDM into IDM++.
- Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior19
A novel approach to launch a backdoor attack with multiple triggers against learned image compression models by employing trained trigger injection models and making slight modifications to the encoder parameters of the compression model is proposed.
- 19
- Video retargeting with multi-scale trajectory optimization19
Video retargeting is formulated as the problem of finding an optimal trajectory for a cropping window to go through the video, capturing the most salient region to scale towards proper display on the target.
- From Data to Knowledge18
The deep learning model compression is investigated and its promise use is demonstrated through a set of experiments and the necessity, importance and open problems regarding the standardization of deep learning models, which enables the interoperability with the standardized compact model representation bitstream syntax, are discussed.
- 18
- Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval18
Nested Invariance Pooling (NIP), a method inspired from i-theory, a mathematical theory for computing group invariant transformations with feed-forward neural networks, is able to produce compact and well-performing descriptors with visual representations extracted from convolutional neural networks.
- Per-Sample Multiple Kernel Approach for Visual Concept Learning18
A per-sample multiple kernel learning approach to take into account intraclass diversity for improving discrimination in visual concept learning, comparable to the state of the art, which has outperformed a canonical MKL.
- 17
- Exploring Model Transferability through the Lens of Potential Energy16
This work reframe the challenge of model selection through the lens of potential energy and directly model the interaction forces that influence fine-tuning dynamics, which can acquire an enhanced and more stable observation for estimating transferability.
- 16
- DeepShoe: An improved Multi-Task View-invariant CNN for street-to-shop shoe retrieval15
An improved Multi-Task View-invariant Convolutional Neural Network (MTV-CNN+) is proposed to handle the large visual discrepancy for the same shoe in different scenarios and an attribute-based weighting scheme on the conventional triplet loss function to put more emphasis on the hard triplets is developed.
- Interactive ads recommendation with contextual search on product topic space15
A ad domain based concept hierarchy is built to make the most of the product details over the e-commerce sites to provide effective advertising suggestions and users can interactively select keyframes or keywords to personalize their intentions by textual re-search.
- Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation14
This paper introduces a novel region-integrated method ReCAP, a probabilistic region modeling scheme that flexibly captures semantic changes in embedding space and develops a finite-to-infinite asymptotic approximation that transforms the intractable region confidence into a tractable and upper-bounded proxy.
- 14
- 13
- 13
- 13
- 13
- 13
- Learning Compact Visual Descriptors for Low Bit Rate Mobile Landmark Search13
This article introduces the work on low bit rate mobile landmark search, in which a compact yet discriminative landmark image descriptor is extracted by using location context such as GPS, crowd-sourced hotspot WLAN, and cell tower locations.
- A Generic Approach for Systematic Analysis of Sports Videos13
A systematic and generic approach to event detection scenario of an input video with an orderly sequential process which is experimented on a relatively large-scale sports consortia and can be widely applied in processing massive videos generically.
- Audio keyword generation for sports video analysis13
This work presents a flexible Hidden Markov Model (HMM)-based audio keyword generation system that treats an audio keyword as a continuous time series data and employs hidden states transition to capture contexts.
- Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm12
This work presents an integrated multiple deep learning models reuse and prediction strategy, which greatly increases the feasibility of the digital retina in processing and analyzing the large-scale visual data in smart cities.
- 12
- Multi-Scale Context Attention Network for Image Retrieval12
This work proposes a Multi-Scale Context Attention Network (MSCAN) to generate global descriptors, which is able to selectively focus on the informative regions with the assistance of multi-scale context information, and model the multi- scale context information by an improved Long Short-Term Memory network across different layers.
- Transfer metric learning: algorithms, applications and outlooks11
A systematic review of the TML literature is presented, group TML into different categories according to different settings and metric transfer strategies, such as direct metric approximation, subspace approximation, distance approximation, and distribution approximation.
- Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach11
A content-adaptive diffusion model for scalable image compression that enables elegant compression ratio control by flexibly selecting intermediate diffusion states, eliminating the need for deep learning model re-training at different operating points is presented.
- Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation11
This work proposes a Neighborhood Consensus Contrastive Learning (NCCL) method, which ensures the compatibility without impairing the accuracy of the new model, and proposes a scheme to filter the old embeddings with low credibility, improving the compatibility robustness.
- Intrinsic Performance Influence-based Participant Contribution Estimation for Horizontal Federated Learning11
A novel contribution estimation method is proposed: Intrinsic Performance Influence-based Contribution Estimation (IPICE), which assigns small contributions to bad/garbage data and thus prevent them from participating and deteriorating the learning ecosystem.
- Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning11
A feature-level prototype loss is proposed to explicitly align two types of embedding features, by transferring global prototype information, and a component-level mutual structural regularization is designed to implicitly optimize the feature intrinsic structure.
- Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image11
Experimental results demonstrate that the proposed mask-Pix2Pix network can well recover missing information of overexposure and outperforms the state of the arts originally designed for image reconstruction tasks.
- Affinity Preserving Quantization for Hashing: A Vector Quantization Approach to Learning Compact Binary Codes11
A novel vector quantization method named affinity preserving quantization (APQ) is proposed to improve the quantization quality of projection values, which has significantly boosted the performance of state-of-the-art hashing techniques.
- Grid-Based Retargeting with Transformation Consistency Smoothing11
This work revisits the retargeting process as working out an optimal mapping function to approximate the output (desirable pixel-wise or region-wise changes) from the training data, and adopts a prediction error decomposition strategy to measure the effectiveness of the previousretargeting methods.
- 11
- Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems10
This work theoretically proves that the conditional entropy of inputs given intermediate features provides a guaranteed lower bound on the reconstruction mean square error (MSE) under any MIA, and derives a differentiable and solvable measure for bounding this conditional entropy based on the Gaussian mixture estimation and proposes a conditional entropy maximization (CEM) algorithm to enhance the inversion robustness.
- 10
- 10
- 10
- Nonparametric motion model with applications to camera motion pattern classification10
The mean shift procedure is employed to propose a novel nonparametric motion representation that can be applied to camera motion pattern classification on 23191 MVF extracted from MPEG-7 dataset.
- Nonparametric color characterization using mean shift10
Experimental results suggest that the color characterization model is much more effective for video indexing and browsing, particularly in the domain of structured video (e.g. sports video).
- LEAD: Exploring Logit Space Evolution for Model Selection9
LEAD proposes a theoretical framework to model the optimization process and derives an ordinary differential equation (ODE) to depict the nonlinear evolution toward the final logit state, and designs a class-aware decomposition method to consider the varying evolution dynamics across classes and further ensure practical applicability.
- 9
- 9
- 9
- 8
- Modeling Uncertain Feature Representation for Domain Generalization8
This paper improves the network generalization ability by modeling domain shifts with uncertainty (DSU), i.e., characterizing the feature statistics as uncertain distributions during training and hypothesizing that the feature statistic, after considering the potential uncertainties, follows a multivariate Gaussian distribution.
- Signal-Independent Separable KLT by Offline Training for Video Coding8
A novel signal-independent separable transform based on the Karhunen–Loève transform (KLT) to improve the efficiency of both intra and inter residual coding and validates the property of signal independency and the strong generalization capacity of the proposed separable KLT.
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- Automatic video genre categorization and event detection techniques on large-scale sports data7
The proposed system firstly identifies the genre of the query video, and then accomplishes the interesting event detection task, which demonstrates the efficiency and accuracy in processing voluminous data from sports collection and achieves various tasks in video analysis.
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- Fast and robust video clip search using index structure5
The mrkd-tree index structure and the proposed video representation are employed to fulfill fast and robust search of short video clips in large video collections with the total length of 15 hours.
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- A generic approach to classify sports video shots and its application in event detection4
This work proposes a generic approach to classify shots in sports video that utilizes bag of visual words model to represent key frame for each shot based on Scale Invariant Feature Transform (SIFT) feature points and applies the results of shot type to detect events in basketball video via a generative-discriminative model.
- Shot-Level Camera Motion Estimation Based on a Parametric Model.4
The design of rules and related parameters’ tuning is significant but difficult to cover many cases from diverse scene contents, various sizes of camera shots makes it infeasible to secure a proper parametric assumption of camera motion as the global motion in large amounts of video data.
- Shot Classification of Sports Video Based on Features in Motion Vector Field4
A novel approach for tennis video analysis is presented, which can automatically classify video shots into 5 classes based on MPEG motion vectors and other features, and derive semantic annotation for all shot classes.
- 3
- 3
- See Through the Windshield from Surveillance Camera3
A windshield image restoration generative adversarial network (WIRE-GAN) to restore and enhance the visibility of windshield images and introduces a novel content-preserving strategy into the proposed weakly-supervised framework to generate more semantically consistent results.
- 3
- 3
- 3
- 3
- DM-PCL: Text-Driven Dual-Modal Prototype Consistency Learning for Weakly-Supervised Few-Shot Part Segmentation2
Text-driven dual-modal prototype consistency learning (DM-PCL) is proposed, which predicts pseudo masks for both support and query images using part-level textual labels and learns consistent part prototypes across diverse images and modalities to facilitate accurate part segmentation.
- 2
- Coding for Intelligence from the Perspective of Category2
A novel problem of Coding for Intelligence from the category theory view is formulated, and a general framework to understand existing methodologies is derived, namely that, coding captures the intrinsic relationships of objects as much as possible, while ignoring information irrelevant to downstream tasks.
- Improving object detection with region similarity learning2
The proposed triplet embedding has improved the performance of well-known Fas-tRCNN model with a mAP gain of 2.1%.
- 2
- 2
- Learning from mobile contexts to minimize the mobile location search latency2
This work combines location related side information from the mobile devices to adaptively supervise the compact visual descriptor design in a flexible manner, which is very suitable to search locations or landmarks within a bandwidth constraint wireless link.
- Linking Traditional TV Advertising to Internet Advertising2
This work presents the current research efforts in the field of analyzing TV ads as well as linking TV ads with relevant Internet ads, and suggests how to collect correlated advertisements across multiple media platforms such as TV and Internet would see significant growth potential in cross-media marketing campaigns.
- Nonparametric motion model2
This work presents a novel nonparametric motion model that bases the motion characterization on the classification of motion patterns and elegantly incorporates the spatial-range information for noise removal and discontinuity preserving smoothing of MVF.
- Enabling Real-World Supervised Video Anomaly Detection: New Open-Set Benchmark and New Framework1
This paper constructs the Real-world Supervised Open-set Benchmark (RSOB) built on a novel large-scale traffic abnormal event dataset with precise frame-level annotation, and proposes a human-prior-aware framework that learns domain-agnostic normality rules through a novel Human-Prior-Focused (HPF) feature space.
- 1
- SEVA: Leveraging Single-Step Ensemble of Vicinal Augmentations for Test-Time Adaptation1
This paper proposes a novel TTA approach named Single-step Ensemble of Vicinal Augmentations (SEVA), which can take advantage of data augmentations without increasing the computational burden and proposes to optimize an upper bound of the entropy loss to integrate the effects of multiple rounds of augmentation training into a single step.
- Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts1
Dual Uncertainty Optimization (DUO) is proposed, the first TTA framework designed to jointly minimize both uncertainties for robust M3OD, and extensive experiments demonstrate the superiority of DUO over existing methods across various datasets and domain shift types.
- Switchable Representation Learning Framework with Self-Compatibility1
A Switchable representation learning Framework with Self-Compatibility (SFSC), which generates a series of compatible sub-models with different capacities through one training process and achieves state-of-the-art performance on the evaluated datasets.
- 1
- 1
- 1
- 1
- 1
- 1
- Interactive service recommendation based on ad concept hierarchy1
This paper aims to produce interactive service recommendation based on ad concept hierarchy by linking web videos, especially ad videos, with informative product details over the commercial websites by introducing the domain based concept hierarchy.
- Clear face analysis from MPEG compressed video1
A system to analyze the clear degree of faces present in MPEG compressed video of Head-and-Shoulders style using low-level features extraction, robust face tracking, and clear faces selection that has integrated the core algorithm into an Automated Transaction Service (ATS) surveillance system.
- –
- –
- –
- –
- –
- Sparse Reasoning is Enough: Biological-Inspired Framework for Video Anomaly Detection with Large Pre-trained Models–
ReCoVAD is proposed, a novel framework inspired by the dual reflex and conscious pathways of the human nervous system, enabling selective frame processing to reduce redundant computation and demonstrate that sparse reasoning is sufficient for effective large-model-based VAD.
- –
- –
- –
- Allocating images and selecting image collections for distributed visual search–
This paper employs Latent Dirichlet Allocation (LDA) to discover the latent concepts as an intermediate semantic representation over a large scale image database and aims to learn an optimal image allocation for each server node and accurately perform collection selection for each query.
- –
- –
- –
- AdVR: Linking Ad Video with Products or Service–
This demonstration attempts to build a semantic linking between ad video and relevant products or service by progressive search on E-commerce websites by exploiting the attractiveness and effectiveness of the approach which semantically links video content with web services.
- –
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 2026-10-12. 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.