Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks213 from public data
- A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance641
This paper proposes a novel deep learning-based approach to PROgressive Vehicle re-ID, called “PROVID”, which treats vehicle Re-Id as two specific progressive search processes: coarse-to-fine search in the feature space, and near- to-distantsearch in the real world surveillance environment.
- 561
- FastReID: A Pytorch Toolbox for General Instance Re-identification465
This work presents FastReID as a widely used software system that supports single and multiple GPU servers, it can reproduce the project results very easily, and has implemented some state-of-the-art projects, including person re-id, partial re-ids, cross-domain re-ID, and vehicle re-identification.
- 443
- Monocular, One-stage, Regression of Multiple 3D People356
ROMP is the first real-time implementation of monocular multi-person 3D mesh regression, and achieves superior performance on the challenging multi- person benchmarks, including 3DPW and CMU Panoptic.
- Gait Recognition in the Wild with Dense 3D Representations and A Benchmark289
This paper proposes a novel framework to explore the 3D Skinned Multi-Person Linear (SMPL) model of the human body for gait recognition, named SMPLGait, and provides 3D SMPL models recovered from video frames which can provide dense 3D information of body shape, viewpoint, and dynamics.
- Recent Advances of Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective246
This article comprehensively summarize the 2D and 3D representations of human body and summarizes the mainstream and milestone approaches for these human body presentations since the year 2014 under unified frameworks to provide a comprehensive and holistic 2D-to-3D perspective.
- Foreground-Aware Pyramid Reconstruction for Alignment-Free Occluded Person Re-Identification228
An alignment-free matching approach namely Foreground-aware Pyramid Reconstruction (FPR) is developed to accurately compute matching scores between occluded persons, regardless of their different scales and sizes and a occlusion-sensitive foreground probability generator is designed that focuses more on clean human body parts to robustify the similarity computation with less contamination from occlusions.
- Putting People in their Place: Monocular Regression of 3D People in Depth220
A novel method to infer the poses and depth of multiple people in a single image that out-performs existing methods on depth reasoning, child shape estimation, and robustness to occlusion.
- Group-aware Label Transfer for Domain Adaptive Person Re-identification216
A group-aware Label Transfer (GLT) algorithm is proposed, which enables the online interaction and mutual promotion of pseudo-label prediction and representation learning and can better correct the noisy pseudo label in an online fashion and narrow down the search space of the target identity.
- Human Mesh Recovery From Monocular Images via a Skeleton-Disentangled Representation201
A skeleton-disentangled based framework is proposed, which divides this task into multi-level spatial and temporal granularity in a decoupling manner, and an effective and pluggable “disentangling the skeleton from the details” (DSD) module is proposed.
- 200
- Hierarchical LSTM with Adjusted Temporal Attention for Video Captioning171
The proposed framework utilizes the temporal attention for selecting specific frames to predict the related words, while the adjusted temporal attention is for deciding whether to depend on the visual information or the language context information.
- Content-Consistent Matching for Domain Adaptive Semantic Segmentation168
This paper considers the adaptation of semantic segmentation from the synthetic source domain to the real target domain and proposes a content-consistent matching (CCM) model, which can alleviate the domain bias caused by those content-irrelevant synthetic images.
- T-C3D: Temporal Convolutional 3D Network for Real-Time Action Recognition145
A new real-time action recognition architecture, called Temporal Convolutional 3D Network (T-C3D), which learns video action representations in a hierarchical multi-granularity manner, demonstrating comparable recognition performance to the state-of-the-art methods.
- Guided Saliency Feature Learning for Person Re-identification in Crowded Scenes128
A new matching approach, called Guided Adaptive Spatial Matching (GASM), which expects that each spatial feature in the query can be the most similar spatial features of a person in a gallery to match.
- TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments124
TRACE is the first one-stage method to jointly recover and track 3D humans in global coordinates from dynamic cameras, and achieves state-of-the-art performance on tracking and HPS benchmarks.
- Cross-Modality Transformer With Modality Mining for Visible-Infrared Person Re-Identification124
This work proposes a new cross-modality transformer-based method (CMTR) for this visible-infrared person re-identification task, which can explicitly mine the information of each modality and generate better discriminative features based on it, and is the first exploration of applying pure transformer network to the cross- modality re-Identification task.
- Hierarchical Gumbel Attention Network for Text-based Person Search106
A novel hierarchical Gumbel attention network for text-based person search via Gumbels top-k re-parameterization algorithm that adaptively selects the strong semantically relevant image regions and words/phrases from images and texts for precise alignment and similarity calculation.
- 89
- MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification82
This work proposes an edge features enhancement module to enhance the modality-sharable features in each single-modality space and designs a perceptual edge features (PEF) loss after the edge fusion strategy analysis, which markedly improves the network's performance.
- 82
- Third-Eye76
Two deep learning models are leveraged, Convolutional Neural Network for images and Long Short Term Memory network for weather and air-pollution data, to build an end-to-end framework for training PM2.5 inference models.
- 75
- Learning Efficient Spatial-Temporal Gait Features with Deep Learning for Human Identification74
A gait energy image (GEI) based Siamese neural network is proposed to automatically extract robust and discriminative spatial gait features for human identification and this framework impressively outperforms state-of-the-art methods.
- Structured Two-Stream Attention Network for Video Question Answering73
This paper proposes a Structured Two-stream Attention network, namely STA, to answer a free-form or open-ended natural language question about the content of a given video to infer rich longrange temporal structures in videos using the authors' structured segment component and encode text features.
- Learnable Aggregating Net with Diversity Learning for Video Question Answering70
A novel architecture, namely Learnable Aggregating Net with Diversity learning (LAD-Net), for V-VQA, which automatically aggregates adaptively-weighted frame-level features to extract rich video (or question) context semantic information by imitating Bags-of-Words (BoW) quantization.
- 70
- Parsing is All You Need for Accurate Gait Recognition in the Wild64
The experimental results show a significant improvement in accuracy brought by the GPS representation and the superiority of ParsingGait, the first parsing-based dataset for gait recognition in the wild, by extending the large-scale and challenging Gait3D dataset.
- Explainable Person Re-Identification with Attribute-guided Metric Distillation62
This paper proposes a post-hoc method, named Attribute-guided Metric Distillation (AMD), to explain existing ReID models, and proposes an attribute prior loss to make the interpreter generate attribute-guided attention maps and to eliminate biases caused by the imbalanced distribution of attributes.
- DELTA: A deep dual-stream network for multi-label image classification62
A novel deep Dual-stream nEtwork for the muLTi-lAbel image classification task, DELTA, which significantly outperforms several state-of-the-art methods and can automatically locate the key image patterns that trigger the labels.
- Gait Recognition in the Wild with Multi-hop Temporal Switch61
A novel multi-hop temporal switch method to achieve effective temporal modeling of gait patterns in real-world scenes and achieves high efficiency with fewer model parameters and reduces the difficulty in optimization compared with 3D convolution-based models.
- Beyond Human-level License Plate Super-resolution with Progressive Vehicle Search and Domain Priori GAN60
The results on a new collected real-world dataset demonstrate that the proposed method achieves the beyond human-level license plate super-resolution performance for automatic license plate recognition and vehicle search.
- BraidNet57
The proposed BraidNet achieves better performance than the state-of-the-art methods for fine-grained human parsing, and a Pairwise Hard Region Embedding strategy is proposed to eliminate the semantic ambiguity of different body parts and clothing.
- Hierarchical multi-view context modelling for 3D object classification and retrieval55
A hierarchical multi-view context modelling method for 3D object classification and retrieval that can imitate the human need to look back and forth to identify and compare the discriminative parts of individual 3D objects based on a joint convolutional neural network and bidirectional long short-term memory network.
- Multi-Granularity Reasoning for Social Relation Recognition From Images51
A pose-guided Person-Object Graph and Person-Pose Graph are proposed to model the actions from persons to object and the interactions between paired persons, respectively and the global features and reasoned knowledge are integrated as a comprehensive representation for social relation recognition.
- A Real-Time Action Representation With Temporal Encoding and Deep Compression50
A new real-time convolutional architecture for action representation, called Temporal Convolutional 3D Network (T-C3D), to capture complementary information on the appearance of a single frame and the motion between consecutive frames and a new temporal encoding method to explore the temporal dynamics of the whole video.
- 49
- Multi-feature Fusion for Predicting Social Media Popularity48
This paper presents the method that underlies the submission to the popularity prediction task of Social Media Prediction Challenge 2017, and chooses the best model to predict the popularity scores of the test images.
- 46
- POINet46
A pose-guided representation network to integrate pose information into hierarchical convolutional features, generating a pose-aligned person representation for person, which helps handle partial occlusions and an ovonic insight network to adaptively encode the cross-frame identity transformation.
- 45
- 43
- 41
- Deep learning based basketball video analysis for intelligent arena application40
A deep learning based video analysis scheme for intelligent basketball arena applications that can automatically select the camera to give high-quality broadcast in real-time and detect the scoring clips as the highlight video reels to support the wonderful actions replay and online sharing functions is proposed.
- Multi-stream Fusion Model for Social Relation Recognition from Videos38
This paper builds a video dataset with 16 categories of social relations annotation according to psychology and sociology studies, named Social Relation In Videos (SRIV), and proposes a multi-stream deep learning model as a benchmark for recognizing social relations.
- Introduction to the Special Issue on Trustworthy Multimedia Computing and Applications in Urban Scenes36
The goal of this special issue (SI) is to encourage a collaborative endeavor to explore the possibilities and obstacles associated with trustworthy multimedia analysis and gather inventive approaches, systems, and applications focused on trustworthy multimedia computing and its applications in urban environments.
- LOCO: Local Context Based Faster R-CNN for Small Traffic Sign Detection33
A LOcal COntext based Faster R-CNN (LOCO) approach for traffic sign detection, which utilizes the regional proposal network for proposal generation, and local context information surrounding proposals for classifying and a local context layer designed to automatically extract the discriminative information from the regions around the proposal objects.
- Deep learning hashing for mobile visual search33
This paper presents a comprehensive survey of the existed deep learning based hashing methods, which showcases their remarkable power of automatic learning highly robust and compact binary code representation for visual search.
- FasterPose: A Faster Simple Baseline for Human Pose Estimation32
This article proposes a design paradigm for cost-effective network with LR representation for efficient pose estimation, named FasterPose, and forms a novel regressive cross-entropy (RCE) loss function for accelerating the convergence and promoting the accuracy.
- 32
- KTAN: Knowledge Transfer Adversarial Network31
A knowledge transfer adversarial network method which holistically considers both intermediate representations and probability distributions of a teacher network and can significantly improve the performance of a student network on two important vision tasks, image classification and object detection.
- 30
- 30
- 29
- 27
- 27
- 23
- 22
- Deep Recurrent Quantization for Generating Sequential Binary Codes21
This work proposes a Deep Recurrent Quantization (DRQ) architecture which can generate sequential binary codes and achieves comparable or even better performance compared with the state-of-the-art for image retrieval.
- 20
- 20
- Correlation Discrepancy Insight Network for Video Re-identification20
A novel correlation discrepancy insight network for video-based person ReID is proposed, which consists of an unsupervised correlation insight model for video purification and a discrepancy description network (DDN) for person representation that outperforms several state-of-the-art methods.
- 20
- 20
- 19
- 19
- 19
- 19
- 18
- Consistency-Constancy Bi-Knowledge Learning for Pedestrian Detection in Night Surveillance17
A consistency-constancy bi-knowledge learning (CCBL) for pedestrian detection in night surveillance is proposed, which is able to simultaneously achieve the night pedestrian detection's useful knowledge, coming from day and night surveillance.
- 17
- 16
- 16
- 15
- 15
- 14
- 14
- 13
- 13
- 12
- 12
- 11
- Effective and Efficient: Toward Open-world Instance Re-identification11
This tutorial would be useful for multimedia content analysis and system-level multimedia retrieval, especially for an effective and efficient open-world ReID system for the practical, large-scale, and open-set domain.
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- Towards Causality Inference for Very Important Person Localization5
A causal inference framework is established that unpacks the causes of previous methods and derives a new principled solution for VIPLoc, which treats the scene as confounding factor, allowing the ever-elusive confounding effects to be eliminated and the essential determinants to be uncovered.
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- How to Understand Named Entities: Using Commonsense for News Captioning–
Commonsense knowledge is exploited to understand named entities for news captioning by correlating the news content with commonsense in the wild, which helps an agent to distinguish semantically similar named entities and describe named entities using words outside of training corpora.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.