342 citations · 555 across the 28 of their papers we have counts for
28 papers
Link-Context Learning for Multimodal LLMs
Yan Tai, Weichen Fan, Zhao Zhang +3
The ability to learn from context with novel concepts, and deliver appropriate responses are essential in human conversations. Despite current Multimodal Large Language Models (MLL…
Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities
Kaijian Liu, Shixiang Tang, Ziyue Li +4
Person clustering with multi-modal clues, including faces, bodies, and voices, is critical for various tasks, such as movie parsing and identity-based movie editing. Related method…
Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
Keqin Chen, Zhao Zhang, Weili Zeng +3
In human conversations, individuals can indicate relevant regions within a scene while addressing others. In turn, the other person can then respond by referring to specific region…
Described Object Detection: Liberating Object Detection with Flexible Expressions
Chi Xie, Zhao Zhang, Yixuan Wu +3
Detecting objects based on language information is a popular task that includes Open-Vocabulary object Detection (OVD) and Referring Expression Comprehension (REC). In this paper,…
Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning
Shaofeng Zhang, Feng Zhu, Rui Zhao +1
We propose ADCLR: A ccurate and D ense Contrastive Representation Learning, a novel self-supervised learning framework for learning accurate and dense vision representation. To ext…
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
Xiaoshi Wu, Yiming Hao, Keqiang Sun +4
Recent text-to-image generative models can generate high-fidelity images from text inputs, but the quality of these generated images cannot be accurately evaluated by existing eval…
Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions
Weizhen He, Yiheng Deng, Shixiang Tang +9
Human intelligence can retrieve any person according to both visual and language descriptions. However, the current computer vision community studies specific person re-identificat…
Advancing Referring Expression Segmentation Beyond Single Image
Yixuan Wu, Zhao Zhang, Xie Chi +2
Referring Expression Segmentation (RES) is a widely explored multi-modal task, which endeavors to segment the pre-existing object within a single image with a given linguistic expr…
CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching
Xiaoshi Wu, Feng Zhu, Rui Zhao +1
Open-vocabulary detection (OVD) is an object detection task aiming at detecting objects from novel categories beyond the base categories on which the detector is trained. Recent OV…
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
Shixiang Tang, Cheng Chen, Qingsong Xie +9
Human-centric perceptions include a variety of vision tasks, which have widespread industrial applications, including surveillance, autonomous driving, and the metaverse. It is des…
Human Preference Score: Better Aligning Text-to-Image Models with Human Preference
Xiaoshi Wu, Keqiang Sun, Feng Zhu +2
Recent years have witnessed a rapid growth of deep generative models, with text-to-image models gaining significant attention from the public. However, existing models often genera…
Saliency Guided Contrastive Learning on Scene Images
Meilin Chen, Yizhou Wang, Shixiang Tang +6
Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still…
Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains
Haiyang Yang, Meilin Chen, Yizhou Wang +5
Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised lea…
DOTIN: Dropping Task-Irrelevant Nodes for GNNs
Shaofeng Zhang, Feng Zhu, Junchi Yan +2
Scalability is an important consideration for deep graph neural networks. Inspired by the conventional pooling layers in CNNs, many recent graph learning approaches have introduced…
GPS: A Policy-driven Sampling Approach for Graph Representation Learning
Tiehua Zhang, Yuze Liu, Xin Chen +3
Graph representation learning has drawn increasing attention in recent years, especially for learning the low dimensional embedding at both node and graph level for classification…
DronePose: The identification, segmentation, and orientation detection of drones via neural networks
Stirling Scholes, Alice Ruget, German Mora-Martin +3
The growing ubiquity of drones has raised concerns over the ability of traditional air-space monitoring technologies to accurately characterise such vehicles. Here, we present a CN…
Feature Erasing and Diffusion Network for Occluded Person Re-Identification
Zhikang Wang, Feng Zhu, Shixiang Tang +3
Occluded person re-identification (ReID) aims at matching occluded person images to holistic ones across different camera views. Target Pedestrians (TP) are usually disturbed by No…
Revisiting the Transferability of Supervised Pretraining: an MLP Perspective
Yizhou Wang, Shixiang Tang, Feng Zhu +4
The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on unsupervised pretraining methods shows superior transfer performance to their supervis…
Real-time, low-cost multi-person 3D pose estimation
Alice Ruget, Max Tyler, Germán Mora Martín +7
The process of tracking human anatomy in computer vision is referred to pose estimation, and it is used in fields ranging from gaming to surveillance. Three-dimensional pose estima…
Improving Facial Attribute Recognition by Group and Graph Learning
Zhenghao Chen, Shuhang Gu, Feng Zhu +2
Exploiting the relationships between attributes is a key challenge for improving multiple facial attribute recognition. In this work, we are concerned with two types of correlation…
Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report
Andrey Ignatov, Grigory Malivenko, Radu Timofte +28
Camera scene detection is among the most popular computer vision problem on smartphones. While many custom solutions were developed for this task by phone vendors, none of the desi…
Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
Shijie Yu, Feng Zhu, Dapeng Chen +5
Recent years have witnessed significant progress in person re-identification (ReID). However, current ReID approaches still suffer from considerable performance degradation when un…
Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
Yixiao Ge, Xiao Zhang, Ching Lam Choi +6
The recent studies of knowledge distillation have discovered that ensembling the "dark knowledge" from multiple teachers or students contributes to creating better soft targets for…
Unsupervised Continual Learning Via Pseudo Labels
Jiangpeng He, Fengqing Zhu
Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However…