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
- Zhan Ping SongSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works172 from public data
- Recent advances and trends in visual tracking: A review651
The goal of this paper is to review the state-of-the-art progress on visual tracking methods, classify them into different categories, as well as identify future trends.
- Deep Industrial Image Anomaly Detection: A Survey514
This paper provides a comprehensive review of deep learning-based image anomaly detection techniques, from the perspectives of neural network architectures, levels of supervision, loss functions, metrics and datasets.
- 428
- Deep 3D human pose estimation: A review402
A thorough review of existing deep learning based works for 3D pose estimation is provided, the advantages and disadvantages of these methods are summarized, and the commonly-used benchmark datasets are explored for comparison and analysis.
- Video Understanding With Large Language Models: A Survey332
The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended multi-granularity (abstract, temporal, and spatiotemporal) reasoning combined with common-sense knowledge, suggesting a promising path for future video understanding.
- Deep Spectral Clustering Using Dual Autoencoder Network313
A joint learning framework for discriminative embedding and spectral clustering is proposed, which can significantly outperform state-of-the-art clustering approaches and be more robust to noise.
- 265
- End-to-End Dense Video Captioning with Parallel Decoding260
Without bells and whistles, extensive experiments show that PDVC is capable of producing high-quality captioning results, surpassing the state-of-the-art two-stage methods when its localization accuracy is on par with them.
- FREE: Feature Refinement for Generalized Zero-Shot Learning229
A feature refinement module that in-corporates semantic→visual mapping into a unified generative model to refine the visual features of seen and unseen class samples, and a self-adaptive margin center loss (SAMC-loss) that cooperates with a semantic cycle-consistency loss to guide FR to learn class- and semantically-relevant representations.
- Prompting for Multi-Modal Tracking215
A novel multi-modal prompt tracker (ProTrack), which can transfer the multi- modal inputs to a single modality by the prompt paradigm, and can achieve high-performance multi- Modal tracking by only altering the inputs, even without any extra training on multi-Modal data.
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models178
A highly transferable Set-level Guidance Attack (SGA) that thoroughly leverages modality interactions and incorporates alignment-preserving augmentation with cross-modal guidance is proposed that could generate adversarial examples that can strongly transfer across different VLP models on multiple downstream vision-language tasks.
- 159
- IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing141
A uniform IM benchmark is proposed, for the first time, to assess how well IAD algorithms perform, which includes various levels of supervision, learning paradigms, memory usage and inference speed, and efficiency.
- Saliency-Associated Object Tracking141
This paper proposes a fine-grained saliency mining module to capture the local saliencies of the target that are discriminative for tracking and designs a saliency-association modeling module to associate the captured saliencies together to learn effective correlation representations between the exemplar and the search image for state estimation.
- Class-Aware Contrastive Semi-Supervised Learning140
This work proposes a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL), which is a drop-in helper to improve the pseudo-label quality and enhance the model's robustness in the real-world setting and successfully emphasizes clean label learning and simultaneously reduce noisy label learning.
- Does Thermal Really Always Matter for RGB-T Salient Object Detection?136
A global illumination estimation module to predict the global illuminance score of the image, so as to regulate the role played by the two modalities, and proposes a network named TNet to solve the RGB-T SOD task.
- 130
- DepthTrack: Unveiling the Power of RGBD Tracking130
A new RGBD tracking dataset - Depth-Track - is introduced that has twice as many sequences and scene types than in the largest existing dataset, and three times more objects, and the average length of the sequences, number of deformable objects and the number of annotated tracking attributes have been increased.
- 120
- Deep learning for video object segmentation: a review109
A systematic review of the deep learning-based video segmentation literature, highlighting the pros and cons of each category of approaches and summarising the datasets for training and testing a video object segmentation algorithm.
- A parallel down-up fusion network for salient object detection in optical remote sensing images108
A novel Parallel Down-up Fusion network (PDF-Net) for SOD in optical RSIs, which takes full advantage of the in-path low- and high-level features and cross-path multi-resolution features to distinguish diversely scaled salient objects and suppress the cluttered backgrounds.
- 106
- Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification106
This work proposes a novel approach to viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation and demonstrates that it outperforms the state-of-the-art supervised Re-ID methods.
- EasyNet: An Easy Network for 3D Industrial Anomaly Detection103
This work proposes an easy and deployment-friendly network (called EasyNet) without using pretrained models and memory banks, which is faster than existing methods, and adopts a multi-modality anomaly segmentation network to achieve a precise anomaly map.
- Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection99
This work introduces CNNs-assisted Transformer architecture and proposes a novel RGB-D SOD network with Point-aware Interaction and CNN-induced Refinement (PICR-Net), which achieves competitive results in both quantitative and qualitative comparisons.
- 96
- Negative Label Guided OOD Detection with Pretrained Vision-Language Models95
This paper proposes a novel post hoc OOD detection method, called NegLabel, which takes a vast number of negative labels from extensive corpus databases, and designs a novel scheme for the OOD score collaborated with negative labels.
- 94
- Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression89
Extensive experiments on benchmark datasets against state-of-the-art datasets indicate the proposed novel vectorized prior has better rate-distortion performance and an impressive 3.18x compression speed up, giving the ability to perform real-time, high-quality variational image compression in practice.
- A Bayesian Federated Learning Framework With Online Laplace Approximation87
A novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side is proposed and achieves state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.
- 84
- Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline80
The first Untrimmed Audio-Visual (UnAV-J 00) dataset is introduced, which contains 10K untrimmed videos with over 30K audio-visual events, and a new learning-based framework is formulated, which is capable of fully integrating audio and visual modalities to localize audio- visual events with various lengths and capture dependencies between them in a single pass.
- 80
- 66
- Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models63
This paper designs two complementary types of knowledge-aware prompts for the text encoder to leverage the distinctive characteristics of category-related external knowledge and designs an adaptation head for the visual encoder to aggregate salient attentive visual cues, which establishes discriminative and task-aware visual representations.
- Depth-aided Camouflaged Object Detection60
Inspired by research on biology and evolution, depth information is introduced as an additional cue to help break camouflage, which can provide spatial information and texture-free separation for foreground and background.
- Learning a Multiple Kernel Similarity Metric for kinship verification60
A novel Multiple Kernel Similarity Metric (MKSM) is proposed, in which, different from the Mahalanobis metric, the similarity computation is essentially based on an implicit nonlinear feature transformation.
- Equally-Guided Discriminative Hashing for Cross-modal Retrieval59
This work discovers the connection between semantic structure preserving and discriminative methods, and directly encode multi-label annotations that act as high-level semantic features to build a common semantic structure preserves classifier.
- 57
- 57
- Dual Distribution Alignment Network for Generalizable Person Re-Identification53
This paper proposes an end-to-end Dual Distribution Alignment Network (DDAN) to learn domain-invariant features with dual-level constraints: the domain-wise adversarial feature learning and the identity-wise similarity enhancement.
- 52
- Realistic action recognition via sparsely-constructed Gaussian processes51
This paper proposes a probabilistic framework using Gaussian processes (GPs), which can tackle regression problems with explicit uncertain models, for action recognition, and designs the GPs covariance matrix via the proposed l1 construction and a local approximation (LA) covariance weight updating method.
- Towards Continual Adaptation in Industrial Anomaly Detection50
A novel method named Distribution of Normal Embeddings (DNE), which utilizes the feature distribution of normal training samples from past tasks and not only effectively alleviates catastrophic forgetting in CAD but also can be integrated with SCL methods to further improve their performance.
- 50
- Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs48
A novel architecture, named Skating-Mixer, is introduced, which extends the MLP framework into a multimodal fashion and effectively learns long-term representations through the authors' designed memory recurrent unit (MRU).
- 48
- 46
- Learning cross-view binary identities for fast person re-identification44
This paper proposes to learn cross-view binary identities (CBI) for fast person re-identification by simultaneously minimising their distance in the Hamming space, and maximising the cross-covariance and margin.
- 40
- Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation39
Seminar learning is proposed, a new learning paradigm for semantic segmentation with click-level supervision that achieves the new state-of-the-art performance of 72.51% (mIOU), surpassing previous methods by a large margin of up to 16.88% on the Pascal VOC 2012 dataset.
- 39
- 37
- 33
- 30
- 29
- 29
- 28
- 27
- 27
- 25
- 25
- 25
- 24
- A Coarse-to-fine Pyramidal Model for Person Re-identification via Multi-Loss Dynamic Training.24
A novel coarse-to-fine pyramid model is proposed that not only incorporates local and global information, but also integrates the gradual cues between them that is able to match the cues at different scales and then search for the correct image of the same identity even when the image pair are not aligned.
- 23
- Rethinking Temporal Fusion for Video-Based Person Re-Identification on Semantic and Time Aspect22
A novel general temporal fusion framework to aggregate frame features on both semantic aspect and time aspect and a multi-stage fusion network is explored to fuse richer frame features at multiple semantic levels, which can effectively reduce the information loss caused by the traditional single- stage fusion.
- 20
- 19
- 19
- 18
- 18
- 17
- 17
- 16
- 16
- 15
- 15
- 15
- 15
- Accelerating Vision-Language Pretraining with Free Language Modeling14
This work proposes a new pretraining task, namely, free language modeling (FLM), that enables a 100% prediction rate with arbitrary corruption rates and shows FLM could achieve an impressive 2.5 × pretraining time reduction in comparison to the MLM-based methods, while keeping competitive performance on both vision-language understanding and generation tasks.
- Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer13
This work presents a single-stage emotion recognition approach, employing a Decoupled Subject-Context Transformer (DSCT), for simultaneous subject localization and emotion classification, and introduces DSCT to facilitate interactions between fine-grained subject-context cues in a ''decouple-then-fuse'' manner.
- 13
- 12
- 12
- Camera-Agnostic Person Re-Identification via Adversarial Disentangling Learning12
An Adversarial Disentangling Learning (ADL) framework to decouple camera-related and ID-related features, which can be readily used for camera-agnostic person ReID, and designs an effective solution to approximate and minimize mutual information by transforming it into a discrimination problem.
- Lab2Pix: Label-Adaptive Generative Adversarial Network for Unsupervised Image Synthesis12
This work proposes an unsupervised framework named Lab2Pix to adaptively synthesize images from labels by elegantly considering the particular properties of label to image synthesis task, and designs the generator in a cumulative style which gradually renders synthesized images by fusing features in different levels.
- 11
- 10
- 10
- 10
- 10
- A Part Power Set Model for Scale-Free Person Retrieval10
An end-to-end part power set model with multi-scale features is proposed, which captures the discriminative parts of pedestrians from global to local, and from coarse to fine, enabling part-based scale-free person re-ID.
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- Towards Generic 3D Tracking in RGBD Videos: Benchmark and Baseline7
This paper investigates a novel problem: is it possible to track a generic 3D object in RGBD videos and predict 3D bounding boxes of the object of interest and proposes an effective tracking baseline to estimate 3D bounding boxes for arbitrary objects in RGBD videos, by fusing appearance and spatial information effectively.
- 7
- 7
- A semi-supervised approach for dimensionality reduction with distributional similarity7
This paper proposes a novel diffusion maps based semi-supervised algorithm for dimensionality reduction, visualization and data representation that preserves the local manifold structure in addition to separating samples in different classes, thus facilitates the classification.
- 6
- 6
- 6
- Binarized Neural Networks for Resource-Efficient Hashing with Minimizing Quantization Loss6
This paper proposes a novel learning binary neural network framework to achieve a resource-efficient deep hashing, and provides two theories to demonstrate the necessity and effectiveness of minimizing the quantization losses for both weights and activations.
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 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
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.