76 citations · 216 across the 19 of their papers we have counts for
11 papers · 1 filter
CAE v2: Context Autoencoder with CLIP Target
Xinyu Zhang, Jiahui Chen, Junkun Yuan +10
Masked image modeling (MIM) learns visual representation by masking and reconstructing image patches. Applying the reconstruction supervision on the CLIP representation has been pr…
Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining
Qiang Chen, Jian Wang, Chuchu Han +12
We present a strong object detector with encoder-decoder pretraining and finetuning. Our method, called Group DETR v2, is built upon a vision transformer encoder ViT-Huge~\cite{dos…
U-HRNet: Delving into Improving Semantic Representation of High Resolution Network for Dense Prediction
Jian Wang, Xiang Long, Guowei Chen +3
High resolution and advanced semantic representation are both vital for dense prediction. Empirically, low-resolution feature maps often achieve stronger semantic representation, a…
RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer
Jian Wang, Chenhui Gou, Qiman Wu +4
Recently, transformer-based networks have shown impressive results in semantic segmentation. Yet for real-time semantic segmentation, pure CNN-based approaches still dominate in th…
Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition
Tailin Chen, Desen Zhou, Jian Wang +6
In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel…
UFO: Unified Feature Optimization
Teng Xi, Yifan Sun, Deli Yu +13
This paper proposes a novel Unified Feature Optimization (UFO) paradigm for training and deploying deep models under real-world and large-scale scenarios, which requires a collecti…
Action Quality Assessment with Temporal Parsing Transformer
Yang Bai, Desen Zhou, Songyang Zhang +5
Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences. Existing state-of-the-art meth…
Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
Yanpeng Sun, Qiang Chen, Xiangyu He +7
Freezing the pre-trained backbone has become a standard paradigm to avoid overfitting in few-shot segmentation. In this paper, we rethink the paradigm and explore a new regime: {\e…
Human-Object Interaction Detection via Disentangled Transformer
Desen Zhou, Zhichao Liu, Jian Wang +4
Human-Object Interaction Detection tackles the problem of joint localization and classification of human object interactions. Existing HOI transformers either adopt a single decode…
Implicit Sample Extension for Unsupervised Person Re-Identification
Xinyu Zhang, Dongdong Li, Zhigang Wang +5
Most existing unsupervised person re-identification (Re-ID) methods use clustering to generate pseudo labels for model training. Unfortunately, clustering sometimes mixes different…
MixFormer: Mixing Features across Windows and Dimensions
Qiang Chen, Qiman Wu, Jian Wang +5
While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs…