297 citations · 551 across the 17 of their papers we have counts for
20 papers
Know Your Body: A Harness for Direct and Self-Improving Robot Control with VLMs
Zeyu Lou, Yanhong Zeng, Yong Wang +1
A general-purpose vision-language model can understand a task goal without knowing how a particular robot's motion and functional parts produce the intended effect. We introduce Kn…
SafeLoop: Risk-Aware Rollback for Vision-Language-Action Manipulation
Zeyu Lou, Tianran Zhang, Xinquan Yue +2
Recent vision-language-action (VLA) models are promising for general-purpose manipulation, but long-horizon execution remains fragile. Small state-estimation or control errors can…
GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
Xin Gao, Jiyao Liu, Guanghao Li +8
Recent advancements have explored text-to-image diffusion models for synthesizing out-of-distribution (OOD) samples, substantially enhancing the performance of OOD detection. Howev…
LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models
Yaohui Wang, Xinyuan Chen, Xin Ma +17
This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challengi…
FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation
Jingwen Guo, Hong Liu, Shitong Sun +3
Existing skeleton-based action recognition methods typically follow a centralized learning paradigm, which can pose privacy concerns when exposing human-related videos. Federated L…
Semantic Prompt for Few-Shot Image Recognition
Wentao Chen, Chenyang Si, Zhang Zhang +3
Few-shot learning is a challenging problem since only a few examples are provided to recognize a new class. Several recent studies exploit additional semantic information, e.g. tex…
MetaFormer Baselines for Vision
Weihao Yu, Chenyang Si, Pan Zhou +5
MetaFormer, the abstracted architecture of Transformer, has been found to play a significant role in achieving competitive performance. In this paper, we further explore the capaci…
Exploring Semantic Attributes from A Foundation Model for Federated Learning of Disjoint Label Spaces
Shitong Sun, Chenyang Si, Guile Wu +1
Conventional centralised deep learning paradigms are not feasible when data from different sources cannot be shared due to data privacy or transmission limitation. To resolve this…
Inception Transformer
Chenyang Si, Weihao Yu, Pan Zhou +3
Recent studies show that Transformer has strong capability of building long-range dependencies, yet is incompetent in capturing high frequencies that predominantly convey local inf…
Generalizable Person Re-Identification via Self-Supervised Batch Norm Test-Time Adaption
Ke Han, Chenyang Si, Yan Huang +2
In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain. As an important t…
Mugs: A Multi-Granular Self-Supervised Learning Framework
Pan Zhou, Yichen Zhou, Chenyang Si +3
In self-supervised learning, multi-granular features are heavily desired though rarely investigated, as different downstream tasks (e.g., general and fine-grained classification) o…
MetaFormer Is Actually What You Need for Vision
Weihao Yu, Mi Luo, Pan Zhou +5
Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent…
Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition
Peng Wang, Jun Wen, Chenyang Si +2
Skeleton-based action recognition is widely used in varied areas, e.g., surveillance and human-machine interaction. Existing models are mainly learned in a supervised manner, thus…
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
Wentao Chen, Chenyang Si, Wei Wang +3
Few-shot learning is a challenging task since only few instances are given for recognizing an unseen class. One way to alleviate this problem is to acquire a strong inductive bias…
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition
Chenyang Si, Xuecheng Nie, Wei Wang +3
We consider the problem of semi-supervised 3D action recognition which has been rarely explored before. Its major challenge lies in how to effectively learn motion representations…
Progressive Cluster Purification for Transductive Few-shot Learning
Chenyang Si, Wentao Chen, Wei Wang +2
Few-shot learning aims to learn to generalize a classifier to novel classes with limited labeled data. Transductive inference that utilizes unlabeled test set to deal with low-data…
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
Chenyang Si, Wentao Chen, Wei Wang +2
Skeleton-based action recognition is an important task that requires the adequate understanding of movement characteristics of a human action from the given skeleton sequence. Rece…
Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search
Ya Jing, Chenyang Si, Junbo Wang +3
Text-based person search aims to retrieve the corresponding person images in an image database by virtue of a describing sentence about the person, which poses great potential for…
Pose-Based Two-Stream Relational Networks for Action Recognition in Videos
Wei Wang, Jinjin Zhang, Chenyang Si +1
Recently, pose-based action recognition has gained more and more attention due to the better performance compared with traditional appearance-based methods. However, there still ex…
Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
Chenyang Si, Ya Jing, Wei Wang +2
Skeleton-based action recognition has made great progress recently, but many problems still remain unsolved. For example, most of the previous methods model the representations of…