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
- Victor C. S. LeeSuggested from co-authorship
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works218 from public data
- Practical elimination of near-duplicates from web video search353
The results of 24 queries in a data set of 12,790 videos retrieved from Google, Yahoo! and YouTube show that this hierarchical approach can dramatically reduce redundant video displayed to the user in the top result set, at relatively small computational cost.
- A survey on deep learning-based fine-grained object classification and semantic segmentation337
Four types of deep learning based fine-grained image classification approaches are reviewed, including the general convolutional neural networks (CNNs), part detection based, ensemble of networks based and visual attention based fine -grainedimage classification approaches.
- Multi-View Image Generation from a Single-View193
This paper proposes a novel image generation model termed VariGANs, which combines the merits of the variational inference and the Generative Adversarial Networks (GANs), and generates the target image in a coarse-to-fine manner instead of a single pass which suffers from severe artifacts.
- 178
- 164
- 152
- Learning Spatial Awareness to Improve Crowd Counting151
A novel architecture called SPatial Awareness Network (SPANet) to incorporate spatial context for crowd counting is presented, and the Maximum Excess over Pixels (MEP) loss is proposed to achieve this by finding the pixel-level subregion with high discrepancy to the ground truth.
- 150
- 147
- Rethinking Spatial Invariance of Convolutional Networks for Object Counting140
Inspired by previous work, this work proposes a low-rank approximation accompanied with translation invariance to favorably implement the approximation of massive Gaussian convolution to improve the spatial invariance of convolutional networks.
- DB-LSTM: Densely-connected Bi-directional LSTM for human action recognition140
A Densely-connected Bi-directional LSTM (DB-LSTM) network is proposed to model the visual and temporal associations in both forward and backward directions to boost the effectiveness and robustness of modeling long-range action recognition.
- 131
- Comparison Study of Internet Recommendation System128
A comprehensive survey of the recommender system research aiming to facilitate readers to understand this field is made and most difficulties and future directions are concluded.
- 98
- Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting97
Extensive experiments on four challenging benchmarks show that McML can significantly improve the original multi-column networks and outperform the other state-of-the-art approaches.
- Near-duplicate keyframe retrieval with visual keywords and semantic context89
A novel NDK retrieval approach is proposed by exploring both visual and textual cues from the visual vocabulary and semantic context respectively by linearly fusing both modalities, which is effective and efficient enough for online video search.
- Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images86
A novel deep neural network is proposed to explore a new cross-domain task, Video2Shop, targeting for matching clothes appeared in videos to the exactly same items in online shops, which outperforms the state-of-the-art methods.
- 84
- 72
- 72
- Detection of bird nests in overhead catenary system images for high-speed rail71
This paper addresses the problem of automatic recognition of bird nests for OCS images with a novel framework, which is composed of five steps: adaptive binarization, trunk/branch detection, hovering point detection, streak extraction and pattern learning, for bird nest detection.
- 70
- 68
- 58
- Personalized clothing recommendation combining user social circle and fashion style consistency52
Three social factors (i.e., personal interest, interpersonal interest similarity and interpersonal influence) and fashion style consistency are fused into a unified personalized recommendation model based on probabilistic matrix factorization (PMF).
- Scheduling real-time requests in on-demand data broadcast environments50
A new online preemptive scheduling algorithm, called PRDS that incorporates urgency, data size and number of pending requests for real-time on-demand broadcast system and uses pyramid preemption to optimize performance and reduce overhead is proposed.
- 49
- CRA-Net48
This work proposes a novel end-to-end VQA model, termed Composed Relation Attention Network (CRA-Net), which devise two question-adaptive relation attention modules that can extract not only the fine-grained and precise binary relations but also the more sophisticated trinary relations.
- Video eCommerce47
An advertising system named Video eCommerce to exhibit appropriate product ads to particular users at proper time stamps of videos, which takes into account video semantics, user shopping preference and viewing behavior feedback by a two-level strategy is proposed.
- 45
- VIREO @ TRECVID 2017: Video-to-Text, Ad-hoc Video Search, and Video hyperlinking.45
The systems developed for Video-to-Text (VTT), Ad-hoc Video Search (AVS) and Video Hyper-linking (LNK) tasks at TRECVID 2017 and the achieved results are described.
- Novelty detection for cross-lingual news stories with visual duplicates and speech transcripts44
The novelty and redundancy detection with visual duplicates and speech transcripts for cross-lingual news stories, and approaches on textual features and visual features demonstrate different performance, and measures on visual features are quite effective.
- 43
- 41
- Research on the Matthews Correlation Coefficients Metrics of Personalized Recommendation Algorithm Evaluation41
The present evaluation metrics with its respective advantages and disadvantages are discussed and the results show that the applicability of Matthews correlation coefficient in the relative evaluation work of recommendation algorithm.
- Sketch Recognition with Deep Visual-Sequential Fusion Model39
A deep end-to-end network for sketch recognition, named Deep Visual-Sequential Fusion model (DVSF) is proposed to model the visual and sequential patterns of the strokes, which outperforms the state-of-the-art approaches.
- 38
- 37
- 35
- 35
- 34
- 33
- 32
- 31
- Automatic content understanding with cascaded spatial–temporal deep framework for capsule endoscopy videos31
A general cascaded spatial-temporal deep framework is proposed to understand the most commonly seen contents of whole GI tract videos and significantly reduces the number of images to be checked by endoscopists and segments images of different organs more accurately.
- Accelerating near-duplicate video matching by combining visual similarity and alignment distortion30
A novel approach to accelerate the matching of two video clips by exploiting the temporal coherence property inherent in the keyframe sequence of a video by eliminating the need for exhaustive keyframe-pair comparisons.
- Single-cell electroporation with high-frequency nanosecond pulse bursts: Simulation considering the irreversible electroporation effect and experimental validation29
The cell electroporation characteristics under HFnsPBs from a mechanism perspective is revealed and has important guidance for fields involving the IRE of cells.
- 29
- 28
- Learning Action-guided Spatio-temporal Transformer for Group Activity Recognition28
A novel Action-guided Spatio-Temporal transFormer (ASTFormer) is proposed to capture the interaction relations for group activity recognition by learning action-centric aggregation and modeling spatio-temporal action dependencies.
- Inter-Limb Muscle Synergies and Kinematic Analysis of Hands-and-Knees Crawling in Typically Developing Infants and Infants With Developmental Delay28
A constrained neuromuscular control strategy due to neurological injury in infants with CDD, and such constrain may contribute to the reduced movement smoothness in infant crawling.
- Part-based clothing image annotation by visual neighbor retrieval28
Part-based clothing image annotation in a search and mining framework that addresses the impact of large variations of clothing is alleviated by pose detection and part-based feature alignment.
- On the Selection of Anchors and Targets for Video Hyperlinking26
Insight is provided from the perspective of hubness and local intrinsic dimensionality, which are two statistical properties in assessing the popularity and complexity of data space and two novel algorithms are proposed for low-risk automatic selection of anchors and targets.
- 26
- Towards google challenge26
This paper explores the Google challenge from a new perspective by combing contextual and social information under the scenario of social web by integrating semantic meaning of text, video relevance from related videos, and user interest induced from user videos to robustly determine video category.
- Modeling video hyperlinks with hypergraph for web video reranking26
Experiments show that hypergraph reranking can improve web video retrieval up to 45% over the initial ranked result by the video sharing websites and 8.3% overThe pair-wise based graph reranking in mean average precision (MAP).
- Experimenting VIREO-374: Bag-of-Visual-Words and Visual-Based Ontology for Semantic Video Indexing and search.26
This paper presents the approaches and results of high-level feature extraction and automatic video search in TRECVID-2007, and explores the upper limit of bag-of-visualwords (BoW) approach based upon local appearance features.
- Beyond Semantic Search: What You Observe May Not Be What You Think.25
This paper presents the approaches and results of the four TRECVID 2008 tasks the authors participated in: high-level feature extraction, automatic video search, video copy detection, and rushes summarization.
- Learning to Transfer24
Generalizable Attribute Learning Model (GALM) is proposed to automatically design the neural networks for generalizable attribute learning and fully exploits the Multi-Task Learning and Reinforcement Learning to speed up the search procedure.
- Learning fashion compatibility across categories with deep multimodal neural networks23
A novel multimodal framework to learn fashion compatibility, which simultaneously integrates both semantic and visual embeddings into a unified deep learning model, which outperforms the state-of-the-art approaches.
- 22
- CODAN: Counting-driven Attention Network for Vehicle Detection in Congested Scenes22
The impressive results indicate that vehicle detection and counting can be mutually supportive, which is an important and meaningful finding.
- 21
- CrossNet: Boosting Crowd Counting with Localization21
A novel location-guided framework named CrossNet is proposed for crowd counting, which integrates location supervision into density maps through dual-branch joint training and outperforms the state-of-the-art approaches both in crowd counting and crowd localization.
- Wireless real-time on-demand data broadcast scheduling with dual deadlines20
The experimental results show that the proposed RDDS algorithms can substantially outperform other algorithms under a wide range of scenarios, especially when combining with Non-deferrable Request First policy, which improves the performance significantly.
- 18
- Genesis of a functional astrocyte syncytium in the developing mouse hippocampus18
The results show that the spongiform morphology of individual astrocytes and their spatial organization all reach stationary levels by postnatal day (P) 15 in the hippocampal CA1 region, and anastrocyte syncytium becomes fully operational at P15 in the mouse hippocampus.
- 18
- Personalized multimedia web summarizer for tourist18
The use of multimedia technology in generating intrinsic summaries of tourism related information through an automated process to gather, filter and classify information on various tourist spots on the Web made retrievable for mobile devices is highlighted.
- 17
- Measurement and Analysis of Human Infant Crawling for Rehabilitation: A Narrative Review17
A practical overview of the most relevant measurements in human infant crawling, including acquisition techniques, data processing methods, features extraction, and the potential value in objective assessment of motor function in infancy are provided.
- 17
- 17
- A New Recommendation Algorithm Based on User’s Dynamic Information in Complex Social Network17
This paper proposed a new recommendation algorithm which is based on social user’s dynamic information to solve the cold start problem of traditional collaborative filtering algorithm and also considered the dynamic factors.
- Alteration of Behavioral Inhibitory Control in High-Altitude Immigrants16
It is suggested that long-term exposure to HAs may attenuate BIC during the response inhibition stage and provide valuable insights into the neurocognitive implications of environmental altitude on BIC.
- 16
- A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference15
The experimental results demonstrate that SPEED achieves a peak throughput of 287.41 GOPS and an energy efficiency of 1335.79 GOPS/W at 4-bit precision condition, which shows SPEED’s significant potential for efficient multi-precision DNN inference.
- Real-time Semantic Segmentation with Parallel Multiple Views Feature Augmentation15
A new real-time semantic segmentation network, called MvFSeg, which combines multi-view features and augmented features from the lightweight networks with progressive dense aggregation structures and outperforms existing state-of-the-art methods.
- 15
- 15
- Boosting web video categorization with contextual information from social web15
This paper explores web video categorization from a new perspective, by integrating the model-based and data-driven approaches to boost the performance, and demonstrates the significant improvement of the proposed approach compared to the traditional text based classifiers.
- 14
- 14
- Clothing Style Recognition using Fashion Attribute Detection14
A new framework for clothing style recognition in natural scenes is proposed through the fusion of super-pixel segmentation, saliency detection and Gaussian Mixture Model to recognize the clothing style.
- Exploring dense trajectory feature and encoding methods for human interaction recognition14
A finding that the performance of vector quantization is on par with or even better than other sophisticated feature encoding methods by using dense trajectories in videos is thoroughly analysed.
- 13
- Web video categorization using category-predictive classifiers and category-specific concept classifiers13
A novel three-stage framework is proposed for Web video classification using category-predictive classifiers and category-specific concept classifiers, which integrates contextual features and concept-level semantics induced from visual content.
- 13
- 13
- 12
- 12
- Hierarchical Multi-Task Learning for Diagram Question Answering with Multi-Modal Transformer12
This paper proposes a novel structural parsing-integrated Hierarchical Multi-Task Learning (HMTL) model for diagram question answering based on a multi-modal transformer framework and demonstrates the effectiveness of the proposed HMTL over other state-of-the-art methods.
- A Novel Web Video Event Mining Framework with the Integration of Correlation and Co-Occurrence Information12
Experimental results on large-scale web videos from YouTube demonstrate that the proposed framework outperforms several existing mining methods and obtains good results for web video event mining.
- 12
- Stacked denoising autoencoder for missing traffic data reconstruction via mobile edge computing11
A novel service architecture of traffic sensing based on mobile edge computing where collected data is pre-processed at the edge node and reconstructed at cloud servers, respectively, and a deep-learning-based algorithm called stacked denoising autoencoder for MTDR (SDAE-MTDR) is developed, which aims at maximizing data reconstruction accuracy within limited observation data.
- Near-Duplicate Segments based news web video event mining11
A framework based on the concept of Near-Duplicate Segments (NDSs) which effectively integrates spatial and temporal information is proposed and is shown to be more effective than several existing methods with a significant improvement.
- 10
- Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment10
Multi-Granularity Cross-Domain Alignment (MGCDA) framework is proposed for anomaly segmentation in complex driving environments, which uniquely combines a new Multi-source Domain Adversarial Training (MDAT) module and a novel Cross-domain Anomaly-aware Contrastive Learning (CACL) method to boost the generality of the model.
- Debunking Free Fusion Myth: Online Multi-view Anomaly Detection with Disentangled Product-of-Experts Modeling10
dPoE, a novel multi-view variational autoencoder model that involves a Product-of-Experts (PoE) layer in tacklingMulti-view data, a Total Correction (TC) discriminator in disentangling view-common and view-specific representations, and a joint loss function in wrapping up all components is proposed.
- 10
- A Deep Learning Based Fast-Flux and CDN Domain Names Recognition Method10
A method called Fast-flux and CDN Domains Recognizer (FCDR) to self-learning FF andCDN features and recognition them based on LSTM network so that the FCDR can classify and identify Fast Flux domain name, CDN domainName, other malicious domain names and common non-CDN domain name more accurately.
- Measuring novelty and redundancy with multiple modalities in cross-lingual broadcast news10
Experiments on the TRECVID-2005 cross-lingual news video corpus showed that modalities and measures demonstrate variant performance for novelty and redundancy detection, and the performance on mono-lingUAL topics is better than multilingual topics.
- 9
- 9
- Clothing Extraction by Coarse Region Localization and Fine Foreground/Background Estimation9
An automatic clothing extraction algorithm is proposed, which consists of two phases: coarse clothing region localization with human proportion, and fine foreground/background modeling, which achieves good performance, and has competitive performance with the interactive solution.
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- Reliability-based design for the structure of tower crane under aleatory and epistemic uncertainties7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- Modeling Local Interest Points for Semantic Detection and Video Search at TRECVID 2006.6
In high-level feature extraction, LIPs with both local description and spatial distribution are explored with both local description and spatial distribution for characterizing and sketching semantic concepts respectively for high-level feature extraction and automatic video search.
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- Rethinking the Effect of Uninformative Class Name in Prompt Learning2
Information Disengagement based Associative Prompt Learning can effectively alleviate the phenomenon of learnable context overfitting to base classes, meanwhile, learning more informative semantic representation of base classes by fine-tuning the class name embedding, leading to improved performance on both base and novel classes.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- THMM-CLIP: Task-Guided Hierarchical Multi-Modal Alignment for Rehearsal-Free Class Incremental Learning1
A task-guided hierarchical multi-modal alignment (THMM-CLIP) is proposed, a framework that establishes persistent visual-textual coherence through hierarchical multi-modal alignment (HMA) and robust prompt selection (RPS).
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- VideoMap: Interactive Search System by MCG-ICT-CAS*–
This paper describes the highlights of the interactive search system VideoMap for TRECVID 2009, which has a map based displaying interface, which gives the user a global view about the similarity relationships among the whole video collection, and provides an active annotating manner to quickly localize the potential positive samples.
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 2026-10-16. 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.