780 citations · 986 across the 36 of their papers we have counts for
36 papers
When Large Vision-Language Models Meet Person Re-Identification
Qizao Wang, Bin Li, Xiangyang Xue
Large Vision-Language Models (LVLMs) that incorporate visual models and large language models have achieved impressive results across cross-modal understanding and reasoning tasks.…
Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
Yinxuan Huang, Chengmin Gao, Bin Li +1
Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpo…
Learning Global Object-Centric Representations via Disentangled Slot Attention
Tonglin Chen, Yinxuan Huang, Zhimeng Shen +3
Humans can discern scene-independent features of objects across various environments, allowing them to swiftly identify objects amidst changing factors such as lighting, perspectiv…
Unleashing the Potential of Tracklets for Unsupervised Video Person Re-Identification
Nanxing Meng, Qizao Wang, Bin Li +1
With rich temporal-spatial information, video-based person re-identification methods have shown broad prospects. Although tracklets can be easily obtained with ready-made tracking…
Distribution Aligned Semantics Adaption for Lifelong Person Re-Identification
Qizao Wang, Xuelin Qian, Bin Li +1
In real-world scenarios, person Re-IDentification (Re-ID) systems need to be adaptable to changes in space and time. Therefore, the adaptation of Re-ID models to new domains while…
Image-Text-Image Knowledge Transfer for Lifelong Person Re-Identification with Hybrid Clothing States
Qizao Wang, Xuelin Qian, Bin Li +2
With the continuous expansion of intelligent surveillance networks, lifelong person re-identification (LReID) has received widespread attention, pursuing the need of self-evolution…
Content and Salient Semantics Collaboration for Cloth-Changing Person Re-Identification
Qizao Wang, Xuelin Qian, Bin Li +3
Cloth-changing person re-identification aims at recognizing the same person with clothing changes across non-overlapping cameras. Advanced methods either resort to identity-related…
Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints
Jinyang Yuan, Tonglin Chen, Zhimeng Shen +2
Visual scenes are extremely diverse, not only because there are infinite possible combinations of objects and backgrounds but also because the observations of the same scene may va…
Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection
Fan Shi, Bin Li, Xiangyang Xue
Endowing machines with abstract reasoning ability has been a long-term research topic in artificial intelligence. Raven's Progressive Matrix (RPM) is widely used to probe abstract…
Rethinking Person Re-identification from a Projection-on-Prototypes Perspective
Qizao Wang, Xuelin Qian, Bin Li +2
Person Re-IDentification (Re-ID) as a retrieval task, has achieved tremendous development over the past decade. Existing state-of-the-art methods follow an analogous framework to f…
Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification
Qizao Wang, Xuelin Qian, Bin Li +2
Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and limited training samples.…
Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems
Fan Shi, Bin Li, Xiangyang Xue
The abstract visual reasoning ability in human intelligence benefits discovering underlying rules in the novel environment. Raven's Progressive Matrix (RPM) is a classic test to re…
OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning
Yinxuan Huang, Tonglin Chen, Zhimeng Shen +3
Humans possess the cognitive ability to comprehend scenes in a compositional manner. To empower AI systems with similar capabilities, object-centric learning aims to acquire repres…
Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis
Zhiyu Jin, Xuli Shen, Bin Li +1
Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. Abiding by the tradition in deep learning, DMs are trained and e…
Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model
Mingzhao Yang, Shangchao Su, Bin Li +1
Recently, semi-supervised federated learning (semi-FL) has been proposed to handle the commonly seen real-world scenarios with labeled data on the server and unlabeled data on the…
Chinese Character Recognition with Radical-Structured Stroke Trees
Haiyang Yu, Jingye Chen, Bin Li +1
The flourishing blossom of deep learning has witnessed the rapid development of Chinese character recognition. However, it remains a great challenge that the characters for testing…
Compositional Scene Modeling with Global Object-Centric Representations
Tonglin Chen, Bin Li, Zhimeng Shen +1
The appearance of the same object may vary in different scene images due to perspectives and occlusions between objects. Humans can easily identify the same object, even if occlusi…
Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning
Shangchao Su, Mingzhao Yang, Bin Li +1
Federated learning (FL) enables multiple clients to collaboratively train a global model without disclosing their data. Previous researches often require training the complete mode…
Domain Discrepancy Aware Distillation for Model Aggregation in Federated Learning
Shangchao Su, Bin Li, Xiangyang Xue
Knowledge distillation has recently become popular as a method of model aggregation on the server for federated learning. It is generally assumed that there are abundant public unl…
Compositional Law Parsing with Latent Random Functions
Fan Shi, Bin Li, Xiangyang Xue
Human cognition has compositionality. We understand a scene by decomposing the scene into different concepts (e.g., shape and position of an object) and learning the respective law…
Style Spectroscope: Improve Interpretability and Controllability through Fourier Analysis
Zhiyu Jin, Xuli Shen, Bin Li +1
Universal style transfer (UST) infuses styles from arbitrary reference images into content images. Existing methods, while enjoying many practical successes, are unable of explaini…
Cross-domain Federated Object Detection
Shangchao Su, Bin Li, Chengzhi Zhang +2
Detection models trained by one party (including server) may face severe performance degradation when distributed to other users (clients). Federated learning can enable multi-part…
One-shot Federated Learning without Server-side Training
Shangchao Su, Bin Li, Xiangyang Xue
Federated Learning (FL) has recently made significant progress as a new machine learning paradigm for privacy protection. Due to the high communication cost of traditional FL, one-…
Compositional Scene Representation Learning via Reconstruction: A Survey
Jinyang Yuan, Tonglin Chen, Bin Li +1
Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is th…