619 citations · 6.4k across the 178 of their papers we have counts for
180 papers
MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask
Yupeng Zhou, Daquan Zhou, Zuo-Liang Zhu +3
Recent advancements in diffusion models have showcased their impressive capacity to generate visually striking images. Nevertheless, ensuring a close match between the generated im…
MagicProp: Diffusion-based Video Editing via Motion-aware Appearance Propagation
Hanshu Yan, Jun Hao Liew, Long Mai +2
This paper addresses the issue of modifying the visual appearance of videos while preserving their motion. A novel framework, named MagicProp, is proposed, which disentangles the v…
DOAD: Decoupled One Stage Action Detection Network
Shuning Chang, Pichao Wang, Fan Wang +2
Localizing people and recognizing their actions from videos is a challenging task towards high-level video understanding. Existing methods are mostly two-stage based, with one stag…
Associating Spatially-Consistent Grouping with Text-supervised Semantic Segmentation
Yabo Zhang, Zihao Wang, Jun Hao Liew +4
In this work, we investigate performing semantic segmentation solely through the training on image-sentence pairs. Due to the lack of dense annotations, existing text-supervised me…
Global Knowledge Calibration for Fast Open-Vocabulary Segmentation
Kunyang Han, Yong Liu, Jun Hao Liew +8
Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred…
Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring
Ruyang Liu, Jingjia Huang, Ge Li +3
Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention f…
Temporal Perceiving Video-Language Pre-training
Fan Ma, Xiaojie Jin, Heng Wang +4
Video-Language Pre-training models have recently significantly improved various multi-modal downstream tasks. Previous dominant works mainly adopt contrastive learning to achieve g…
Class Prototype-based Cleaner for Label Noise Learning
Jingjia Huang, Yuanqi Chen, Jiashi Feng +1
Semi-supervised learning based methods are current SOTA solutions to the noisy-label learning problem, which rely on learning an unsupervised label cleaner first to divide the trai…
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…
ManiCLIP: Multi-Attribute Face Manipulation from Text
Hao Wang, Guosheng Lin, Ana García del Molino +3
In this paper we present a novel multi-attribute face manipulation method based on textual descriptions. Previous text-based image editing methods either require test-time optimiza…
Coordinate Attention for Efficient Mobile Network Design
Qibin Hou, Daquan Zhou, Jiashi Feng
Recent studies on mobile network design have demonstrated the remarkable effectiveness of channel attention (e.g., the Squeeze-and-Excitation attention) for lifting model performan…
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
Yifan Zhang, Bryan Hooi, Dapeng Hu +2
Contrastive self-supervised learning (CSL) has attracted increasing attention for model pre-training via unlabeled data. The resulted CSL models provide instance-discriminative vis…
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
Hanshu Yan, Jingfeng Zhang, Gang Niu +3
We investigate the adversarial robustness of CNNs from the perspective of channel-wise activations. By comparing \textit{non-robust} (normally trained) and \textit{robustified} (ad…
ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
Shaofei Huang, Si Liu, Tianrui Hui +4
Learning to capture dependencies between spatial positions is essential to many visual tasks, especially the dense labeling problems like scene parsing. Existing methods can effect…
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Li Yuan, Yunpeng Chen, Tao Wang +6
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT mo…
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
Jian Liang, Dapeng Hu, Yunbo Wang +2
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods…
Improving Generalization in Reinforcement Learning with Mixture Regularization
Kaixin Wang, Bingyi Kang, Jie Shao +1
Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments. To improve their…
Towards Accurate Human Pose Estimation in Videos of Crowded Scenes
Li Yuan, Shuning Chang, Xuecheng Nie +5
Video-based human pose estimation in crowded scenes is a challenging problem due to occlusion, motion blur, scale variation and viewpoint change, etc. Prior approaches always fail…
A Simple Baseline for Pose Tracking in Videos of Crowded Scenes
Li Yuan, Shuning Chang, Ziyuan Huang +6
This paper presents our solution to ACM MM challenge: Large-scale Human-centric Video Analysis in Complex Events\cite{lin2020human}; specifically, here we focus on Track3: Crowd Po…
Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes
Li Yuan, Yichen Zhou, Shuning Chang +6
Detecting and recognizing human action in videos with crowded scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal w…
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning
Pan Zhou, Jiashi Feng, Chao Ma +3
It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide…
Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations
Meng-Jiun Chiou, Roger Zimmermann, Jiashi Feng
Visual relationship detection aims to reason over relationships among salient objects in images, which has drawn increasing attention over the past few years. Inspired by human rea…
Dual Adversarial Auto-Encoders for Clustering
Pengfei Ge, Chuan-Xian Ren, Jiashi Feng +1
As a powerful approach for exploratory data analysis, unsupervised clustering is a fundamental task in computer vision and pattern recognition. Many clustering algorithms have been…
ConvBERT: Improving BERT with Span-based Dynamic Convolution
Zihang Jiang, Weihao Yu, Daquan Zhou +3
Pre-trained language models like BERT and its variants have recently achieved impressive performance in various natural language understanding tasks. However, BERT heavily relies o…