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
- Suggested from co-authorship
- Qi TianSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works177 from public data
- Person Transfer GAN to Bridge Domain Gap for Person Re-identification2,033
A Person Transfer Generative Adversarial Network (PTGAN) is proposed to relieve the expensive costs of annotating new training samples and comprehensive experiments show that the domain gap could be substantially narrowed-down by the PTGAN.
- Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models855
The Qwen-Audio model, a multi-task training framework that achieves impressive performance across diverse benchmark tasks without requiring any task-specific fine-tuning, surpassing its counterparts.
- Pose-Driven Deep Convolutional Model for Person Re-identification843
A Pose-driven Deep Convolutional (PDC) model is proposed to learn improved feature extraction and matching models from end to end and explicitly leverages the human part cues to alleviate the pose variations and learn robust feature representations from both the global image and different local parts.
- 442
- Deep Representation Learning With Part Loss for Person Re-Identification439
Experimental results on three person ReID datasets, i.e., Market1501, CUHK03, and VIPeR, show that the proposed deep representation learning procedure named part loss network outperforms existing deep representations.
- Unsupervised Person Re-Identification via Multi-Label Classification422
This paper formulates unsupervised person ReID as a multi-label classification task to progressively seek true labels by leveraging the updated ReID model for label prediction and proposes the memory-based multi- label classification loss (MMCL).
- GLAD410
A Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework that leverages the local and global cues in human body to generate a discriminative and robust representation are proposed.
- Bi-Directional Cascade Network for Perceptual Edge Detection362
A Bi-Directional Cascade Network (BDCN) structure is proposed, where an individual layer is supervised by labeled edges at its specific scale, rather than directly applying the same supervision to all CNN outputs.
- DR2-Net: Deep Residual Reconstruction Network for image compressive sensing359
A novel Deep Residual Reconstruction Network (DR2-Net) to reconstruct the image from its Compressively Sensed measurement by outperforms traditional iterative methods and recent deep learning-based methods by large margins at measurement rates 0.01, 0.1, and 0.25.
- 345
- Watch, attend and parse: An end-to-end neural network based approach to handwritten mathematical expression recognition259
Watch, Attend and Parse (WAP), a novel end-to-end approach based on neural network that learns to recognize HMEs in a two-dimensional layout and outputs them as one-dimensional character sequences in LaTeX format, significantly outperformed the state-of-the-art method.
- 256
- 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.
- RAM: A Region-Aware Deep Model for Vehicle Re-Identification245
A novel learning algorithm is introduced to jointly use vehicle IDs, types/models, and colors to train the Region-Aware deep Model (RAM), which fuses more cues for training and results in more discriminative global and regional features.
- Intra-Inter Camera Similarity for Unsupervised Person Re-Identification235
This paper targets to address the challenge of degraded accuracy in label computation across cameras by studying a novel intra-inter camera similarity for pseudo-label generation, which produces surprisingly good performance on multiple datasets.
- AAformer: Auto-Aligned Transformer for Person Re-Identification205
An alignment scheme in transformer architecture for the first time is introduced and the auto-aligned transformer (AAformer) is proposed to automatically locate both the human parts and nonhuman ones at patch level to help in person re-identification.
- A glutamatergic reward input from the dorsal raphe to ventral tegmental area dopamine neurons195
It is shown that optogenetic activation of this pathway conveys reward in mice, indicating that the DR–VGluT3 pathway to VTA utilizes glutamate as a neurotransmitter and is a substrate linking the DR—one of the most sensitive reward sites in the brain—to VTA dopaminergic neurons.
- 191
- Multi-Scale 3D Convolution Network for Video Based Person Re-Identification187
Evaluations on three widely used benchmarks datasets, i.e., MARS, PRID2011, and iLIDS-VID demonstrate the substantial advantages of the proposed two-stream convolution network over existing 3D convolution networks and state-of-art methods.
- Dorsal Raphe Dual Serotonin-Glutamate Neurons Drive Reward by Establishing Excitatory Synapses on VTA Mesoaccumbens Dopamine Neurons176
A path-specific input from DR serotonergic neurons to VTA that promotes reward by the release of glutamate and activation of mesoaccumbens dopamine neurons is suggested.
- Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-identification163
This paper tackles the challenge of jointly enforcing visual and temporal consistency in the combination of a local one-hot classification and a global multi-class classification by outperforming recent unsupervised domain adaptive methods, which leverage more labels for training.
- 153
- 153
- Glutamatergic and dopaminergic neurons in the mouse ventral tegmental area144
It is found that low frequency of VGluT2 mRNA (+)/TH‐IR neurons in the mouse is due to lack of synthesis of TH protein, rather than TH protein trafficking.
- Building contextual visual vocabulary for large-scale image applications137
The experimental results show that the contextual visual vocabulary shows significant improvement over the classic visual vocabulary, and outperforms the state-of-the-art Bundled Feature in the terms of retrieval precision, memory consumption and efficiency.
- 122
- Rewarding Effects of Optical Stimulation of Ventral Tegmental Area Glutamatergic Neurons119
It is shown that previously discovered glutamatergic neurons within the ventral tegmental area (VTA), through their local connections, play a role in reward, and that VTA injections of AMPA or NMDA receptor antagonists blocked optical self-stimulation and place preference.
- Large-Scale Spatio-Temporal Person Re-Identification: Algorithms and Benchmark108
This work contributes a novel Large-scale Spatio-Temporal (LaST) person re- ID dataset, including 10,862 identities with more than 228k images, and proposes an easy-to-implement baseline that works well in such challenging re-ID settings.
- 105
- 105
- Multimodal Deep Convolutional Neural Network for Audio-Visual Emotion Recognition105
This paper proposes to bridge the emotional gap based on a multimodal Deep Convolution Neural Network (DCNN), which fuses the audio and visual cues in a deep model, which is trained with two stages.
- 103
- Robust Partial Matching for Person Search in the Wild89
An Align-to-Part Network (APNet) for person detection and re-Identification (reID) is proposed, which refines detected bounding boxes to cover the estimated holistic body regions, from which discriminative part features can be extracted and aligned.
- MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking88
A new dynamic modality-aware filter generation module (named MFGNet) is proposed to boost the message communication between visible and thermal data by adaptively adjusting the convolutional kernels for various input images in practical tracking.
- 87
- 86
- 86
- 76
- 71
- 70
- Multi-type attributes driven multi-camera person re-identification69
A weakly supervised multi-type attribute learning framework which considers the contextual cues among attributes and progressively boosts the accuracy of attributes only using a limited number of labeled data is proposed.
- Viewpoint and Scale Consistency Reinforcement for UAV Vehicle Re-Identification68
A viewpoint adversarial training strategy and a multi-scale consensus loss to promote the robustness and discriminative power of learned deep features in UAV vehicle ReID is proposed.
- 64
- 62
- 62
- 53
- Resolution-invariant Person Re-Identification51
This paper learns person representations robust to resolution variance through jointly training a Foreground-Focus Super-Resolution (FFSR) module and a Resolution-Invariant Feature Extractor (RIFE) by end-to-end CNN learning.
- 50
- 48
- 48
- Ventral tegmental area GABA, glutamate, and glutamate‐GABA neurons are heterogeneous in their electrophysiological and pharmacological properties47
The utility of the double transgenic mouse to access VTA glutamate, glutamate-GABA and GABA neurons is demonstrated, and some electrophysiological heterogeneity among them is shown, including μ-opioid receptor activation hyperpolarizes some VTA neurotransmitter neurons and some GABA-releasing neurons.
- Decoupled Contrastive Learning for Long-Tailed Recognition46
This paper decouples two types of positives in SCL and optimizes their relations toward different objectives to alleviate the influence of the imbalanced dataset, and proposes a patch-based self distillation to transfer knowledge from head to tail classes to relieve the under-representation of tail classes.
- Attributes driven tracklet-to-tracklet person re-identification using latent prototypes space mapping45
This work learns and considers the contextual relations among human attributes, and validate that such cues help person re-identification tasks, and establishes a discriminative feature representation by leveraging the relations between attributes and low-level features within a latent space.
- SCAN: Spatial and Channel Attention Network for Vehicle Re-Identification44
A Spatial and Channel Attention Network (SCAN) based on DCNN is proposed, which contains two branches, i.e., spatial attention branch and channel attention branch, embedded after convolutional layers to refine the feature maps and more discriminative features can be extracted automatically.
- 43
- Domain Adaptive Person Re-Identification via Coupling Optimization42
A coupling optimization method including the Domain-Invariant Mapping (DIM) method and the Global-Local distance Optimization (GLO), respectively, designed to train the ReID model with unsupervised setting on the target domain.
- 39
- Graph Consistency Based Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification37
Experimental results show that proposed Graph Consistency based Mean-Teaching (GCMT) outperforms state-of-the-art methods by clear margin and even outperforms the previous method that uses a deeper backbone.
- SlideSpeech: A Large Scale Slide-Enriched Audio-Visual Corpus34
Through the application of keyword extraction and contextual ASR methods in the benchmark system, the potential of improving speech recognition performance by incorporating textual information from supplementary video slides is demonstrated.
- 31
- VP-ReID30
A robust and efficient person and video ReID system named as VP-ReID is developed, build based on recent works including Deep Convolutional Neural Network design for discriminative feature extraction, efficient off-line indexing, as well as distance metric optimization for deep feature learning.
- Efficient Video Transformers via Spatial-temporal Token Merging for Action Recognition29
A lightweight and plug-and-play module, namely Spatial-temporal Token Merger (STTM), to merge the tokens belonging to the same object into a more compact representation, which substantially decreases the number of tokens that need to be processed by each Transformer block and boosts the efficiency.
- Building descriptive and discriminative visual codebook for large-scale image applications29
This paper gives a comprehensive survey on visual vocabulary and details several state-of-the-art algorithms on descriptive and discriminative visual word generation, and introduces two interesting post processing strategies to further improve the performance of visual vocabulary.
- Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap28
Comprehensive experiments on an unprecedentedly rich variety of low-resource datasets demonstrate consistent and substantial performance improvements, proving that the proposed method of enhancing low-resource ASR through a versatile TTS model is highly effective and has broad application prospects.
- 28
- 27
- 27
- ObjectPatchNet: Towards scalable and semantic image annotation and retrieval25
This work proposes a scalable data-driven solution for annotating and retrieving Web-scale image data from large-scale loosely annotated images a compact and informative representation, namely ObjectPatchNet, and takes it as a visual vocabulary with semantic labels, and is able to easily develop inverted file indexing for efficient semantic image retrieval.
- One-Shot Fine-Grained Instance Retrieval24
Experiments show the OSFGIR framework achieves significantly better accuracy and efficiency than existing FGVC and image retrieval methods, thus could be a better solution for large-scale fine-grained object identification.
- Distillation-Guided Residual Learning for Binary Convolutional Neural Networks22
This work enforces BCNN to produce similar intermediate feature maps with the ones of FCNN to minimize the performance gap, and updates the binary convolutional block architecture to facilitate the optimization of blockwise distillation loss.
- Mutual Information-Based Emotion Recognition22
A general scheme for video emotion identification using mutual information-based feature selection followed by regression to measure video affective content in dimensional arousal-valence space is proposed.
- 21
- 21
- Music video affective understanding using feature importance analysis20
Experimental results demonstrate the proposed novel feature importance analysis approach to select most representative arousal and valence features for arousal andValence modeling has a considerable improvement on music video affective understanding.
- 19
- 18
- E2BoWs: An end-to-end Bag-of-Words model via deep convolutional neural network for image retrieval18
This work proposes an End-to-End BoWs model based on Deep Convolutional Neural Network that takes an image as input, then identifies and separates semantic objects in it, and finally outputs visual words with high semantic discriminative power.
- Decoupled Optimisation for Long-Tailed Visual Recognition16
A multistage parameter Decouple and Optimisation (DO) framework that decouples parameters into different groups with each group learning a specific portion of classes and achieves competitive performance compared to the state-of-the-art.
- 16
- 16
- Multi-Modal Reference Learning for Fine-Grained Text-to-Image Retrieval15
A reference-guided representation learning module is proposed to use multi-modal references to learn more accurate visual and textual representations and a reference-based refinement method that employs the object references to compute a reference-based similarity that refines the initial retrieval results is introduced.
- MFCCA:Multi-Frame Cross-Channel Attention for Multi-Speaker ASR in Multi-Party Meeting Scenario14
A multi-frame cross-channel attention, which models cross- channel information between adjacent frames to exploit the complementarity of both frame-wise and channel-wise knowledge, is proposed.
- 14
- 13
- 13
- Modeling spatial and semantic cues for large-scale near-duplicated image retrieval13
The geometric visual vocabulary which captures the spatial contexts by quantizing local features in bi-space, i.e., in descriptor space and orientation space and the contextual visual vocabulary, which combines both spatial and semantic clues outperforms the state-of-the-art bundled feature in both retrieval precision and efficiency.
- Personalized MTV Affective Analysis Using User Profile13
A novel approach combining support vector regression and psychological affective model to achieve personalized affective analysis is proposed and the experimental results illustrate the effectiveness and advantages of the proposed method.
- Augmented Feature Fusion for Image Retrieval System12
This work adopts the reciprocal neighbor based graph fusion approach for feature fusion and explicitly augments the original approach with the following two strategies: 1) investigates the most suitable feature combinations on various datasets, including the deep learning feature, which has been popular for image retrieval recently; 2) further improves the robustness of originalgraph fusion approach by the SVM prediction strategy.
- Superimage: Packing Semantic-Relevant Images for Indexing and Retrieval12
This work proposes to package semantically relevant images into superimages, and then index superimages instead of single images, which effectively packages multiple images into one new unit, hence significantly decreases the number of images to be indexed.
- Loss Masking Is Not Needed In Decoder-Only Transformer For Discrete-Token-Based ASR11
This paper proposes a novel approach denoted Smoothed Label Distillation (SLD), which applies a KL divergence loss with smoothed labels on speech tokens, which effectively models speech tokens and outperforms Loss Masking for decoder-only Transformers in ASR tasks with different speech discretization methods.
- Anti-Forgetting Adaptation for Unsupervised Person Re-Identification11
A Dual-level Joint Adaptation and Anti-forgetting (DJAA) framework, which incrementally adapts a model to new domains without forgetting source domain and each adapted target domain, and explores the possibility of using prototype and instance-level consistency to mitigate the forgetting during the adaptation.
- 11
- 11
- Efficient Multi-modal Long Context Learning for Training-free Adaptation10
This approach is the first to seamlessly integrate compression and pruning techniques for multi-modal long-context learning, offering a scalable and efficient solution for real-world applications.
- 10
- Diverse part attentive network for video-based person re-identification10
A Diverse Part Attentive Network (DPAN) to exploit discriminative and diverse body cues and achieves competitive performance on these datasets compared with state-of-the-art methods.
- 9
- Multi-order visual phrase for scalable image search9
Multi-order visual phrase is proposed which contains two complementary clues: center visual word quantized from the local descriptor of each image keypoint and the visual and spatial clues of multiple nearby keypoints and is more robust to quantization error than existing visual phrases.
- i.MTV9
Based on the affective analysis and visualization, MTV affective retrieval and management are achieved and novel methods are proposed for user affective preferences analysis and MTV recommendation.
- 8
- 8
- 8
- Learning attribute-aware dictionary for image classification and search8
An Attribute aware Dictionary Learning (AttrDL) scheme to learn multiple sub-dictionaries with specific semantic meanings and shows that the proposed scheme outperforms the state-of-the-art algorithms in both image classification and search tasks.
- 7
- 7
- Recognizing Ultra-High-Speed Moving Objects with Bio-Inspired Spike Camera7
The first theoretical analysis for the causes of spiking motion blur is presented and a robust representation that addresses this issue through temporal-spatial context learning is proposed that outperforms all existing spike-based recognition methods.
- Hybrid Network Compression via Meta-Learning7
This paper incorporates two criteria and seeks layer-wise compression by leveraging the meta-learning framework and proposes an iterative compression constraint for optimizing the compression procedure, which effectively achieves a high compression rate and maintains the original network performance.
- 7
- 7
- 7
- 7
- Scalable mobile search with binary phrase7
This paper proposes to build binary phrase which employs fast binary local descriptor and extracts spatial clues to improve both the efficiency and discriminative power of mobile search systems.
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- HumVis: Human-Centric Visual Analysis System4
HumVis is a robust and efficient human-centric visual analysis system built on a simple yet efficient contextual instance decoupling (CID) module, which can effectively separate different persons in an input image and output corresponding person structure information for visual analysis.
- 4
- 4
- 4
- 4
- 4
- 3
- Introduction to the Special Issue on Fine-Grained Visual Recognition and Re-Identification3
This Special Issue aims to accurately analyze, identify visual objects, and match re-appearing targets, e.g., persons and vehicles from a large set of images and videos, which has the potential to offer an unprecedented possibility for intelligent video processing and analysis.
- 3
- 3
- 3
- 2
- 2
- 2
- Hybrid-Indexing Multi-type Features for Large-Scale Image Search2
A novel hybrid-indexing strategy, which incorporates multiple similarity metrics into one inverted index file during off-line indexing, which could obtain more satisfying retrieval results because the index file conveys hybrid similarities among images.
- Personalized Visual Vocabulary Adaption for Social Image Retrieval2
The personalized visual vocabulary adaption is proposed which removes non-discriminative visual words and replaces them with more exact and discriminative ones, i.e., adapt a general vocabulary toward a specific user's image set, and shows satisfying efficiency.
- Multi-order visual phrase for scalable partial-duplicate visual search2
Multi-order visual phrase (MVP) is proposed which contains two complementary clues: center visual word quantized from the local descriptor of each image keypoint and the visual and spatial clues of multiple nearby keypoints and is more robust to quantization error than existing visual phrases.
- 1
- 1
- MoGE: A Benchmark for Comprehensive Evaluation of Molecular Generation Models in De Novo Drug Design1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Indexing heterogeneous features with superimages1
This work proposes to package semantically relevant images into superimages, and then index superimages instead of single images, which naturally saves the memory cost and retrieval time and is naturally superior to many online retrieval fusion algorithms in terms of retrieval efficiency and memory consumption.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.