502 citations · 1.4k across the 190 of their papers we have counts for
31 papers · 1 filter
Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation
Zhen Zhao, Lihe Yang, Sifan Long +3
Recent studies on semi-supervised semantic segmentation (SSS) have seen fast progress. Despite their promising performance, current state-of-the-art methods tend to increasingly co…
Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers
Yasheng Sun, Hang Zhou, Kaisiyuan Wang +7
Previous studies have explored generating accurately lip-synced talking faces for arbitrary targets given audio conditions. However, most of them deform or generate the whole facia…
Cyclically Disentangled Feature Translation for Face Anti-spoofing
Haixiao Yue, Keyao Wang, Guosheng Zhang +4
Current domain adaptation methods for face anti-spoofing leverage labeled source domain data and unlabeled target domain data to obtain a promising generalizable decision boundary.…
Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition
Jiaxiang Tang, Kaisiyuan Wang, Hang Zhou +6
While dynamic Neural Radiance Fields (NeRF) have shown success in high-fidelity 3D modeling of talking portraits, the slow training and inference speed severely obstruct their pote…
Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentation
Zhen Zhao, Sifan Long, Jimin Pi +2
Recently, semi-supervised semantic segmentation has achieved promising performance with a small fraction of labeled data. However, most existing studies treat all unlabeled data eq…
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers
Sifan Long, Zhen Zhao, Jimin Pi +2
Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Ma…
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…
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…
It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training
Yuxin Song, Min Yang, Wenhao Wu +3
Self-supervised video transformer pre-training has recently benefited from the mask-and-predict pipeline. They have demonstrated outstanding effectiveness on downstream video tasks…
StyleSwap: Style-Based Generator Empowers Robust Face Swapping
Zhiliang Xu, Hang Zhou, Zhibin Hong +7
Numerous attempts have been made to the task of person-agnostic face swapping given its wide applications. While existing methods mostly rely on tedious network and loss designs, t…
NeRF-Loc: Transformer-Based Object Localization Within Neural Radiance Fields
Jiankai Sun, Yan Xu, Mingyu Ding +5
Neural Radiance Fields (NeRFs) have become a widely-applied scene representation technique in recent years, showing advantages for robot navigation and manipulation tasks. To furth…
TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers
Zengyuan Guo, Yuechen Yu, Pengyuan Lv +6
Table structure recognition is a crucial part of document image analysis domain. Its difficulty lies in the need to parse the physical coordinates and logical indices of each cell…
CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval
Haoran Wang, Dongliang He, Wenhao Wu +7
Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative…
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…
Conditional DETR V2: Efficient Detection Transformer with Box Queries
Xiaokang Chen, Fangyun Wei, Gang Zeng +1
In this paper, we are interested in Detection Transformer (DETR), an end-to-end object detection approach based on a transformer encoder-decoder architecture without hand-crafted p…
Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network
Bo Ju, Zhikang Zou, Xiaoqing Ye +4
3D object detection task from lidar or camera sensors is essential for autonomous driving. Pioneer attempts at multi-modality fusion complement the sparse lidar point clouds with r…
Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption
Jiazhi Guan, Hang Zhou, Mingming Gong +3
Despite encouraging progress in deepfake detection, generalization to unseen forgery types remains a significant challenge due to the limited forgery clues explored during training…
Delving into Sequential Patches for Deepfake Detection
Jiazhi Guan, Hang Zhou, Zhibin Hong +4
Recent advances in face forgery techniques produce nearly visually untraceable deepfake videos, which could be leveraged with malicious intentions. As a result, researchers have be…
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…
MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining
Pengyuan Lyu, Chengquan Zhang, Shanshan Liu +7
Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or…
Few-Shot Head Swapping in the Wild
Changyong Shu, Hemao Wu, Hang Zhou +7
The head swapping task aims at flawlessly placing a source head onto a target body, which is of great importance to various entertainment scenarios. While face swapping has drawn m…
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…