343 citations · 2.4k across the 46 of their papers we have counts for
8 papers · 1 filter
Interactive Fusion of Multi-level Features for Compositional Activity Recognition
Rui Yan, Lingxi Xie, Xiangbo Shu +1
To understand a complex action, multiple sources of information, including appearance, positional, and semantic features, need to be integrated. However, these features are difficu…
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
Xiang Li, Wenhai Wang, Xiaolin Hu +3
Localization Quality Estimation (LQE) is crucial and popular in the recent advancement of dense object detectors since it can provide accurate ranking scores that benefit the Non-M…
Causal Intervention for Weakly-Supervised Semantic Segmentation
Dong Zhang, Hanwang Zhang, Jinhui Tang +2
We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only im…
Social Adaptive Module for Weakly-supervised Group Activity Recognition
Rui Yan, Lingxi Xie, Jinhui Tang +2
This paper presents a new task named weakly-supervised group activity recognition (GAR) which differs from conventional GAR tasks in that only video-level labels are available, yet…
Feature Pyramid Transformer
Dong Zhang, Hanwang Zhang, Jinhui Tang +3
Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are pass…
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
Xiang Li, Wenhai Wang, Lijun Wu +5
One-stage detector basically formulates object detection as dense classification and localization. The classification is usually optimized by Focal Loss and the box location is com…
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
Jinshan Pan, Haoran Bai, Jinhui Tang
We present a simple and effective deep convolutional neural network (CNN) model for video deblurring. The proposed algorithm mainly consists of optical flow estimation from interme…
Deep Blind Video Super-resolution
Jinshan Pan, Songsheng Cheng, Jiawei Zhang +1
Existing video super-resolution (SR) algorithms usually assume that the blur kernels in the degradation process are known and do not model the blur kernels in the restoration. Howe…