175 citations · 319 across the 22 of their papers we have counts for
26 papers
Video Understanding: From Geometry and Semantics to Unified Models
Zhaochong An, Zirui Li, Mingqiao Ye +9
Video understanding aims to enable models to perceive, reason about, and interact with the dynamic visual world. In contrast to image understanding, video understanding inherently…
EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark
Deheng Zhang, Yuqian Fu, Runyi Yang +9
Most existing benchmarks for understanding egocentric vision focus primarily on daytime scenarios, overlooking the low-light conditions that are inevitable in real-world applicatio…
ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives
Yuqian Fu, Runze Wang, Bin Ren +6
Bridging the gap between ego-centric and exo-centric views has been a long-standing question in computer vision. In this paper, we focus on the emerging Ego-Exo object corresponden…
XTrack: Multimodal Training Boosts RGB-X Video Object Trackers
Yuedong Tan, Zongwei Wu, Yuqian Fu +7
Multimodal sensing has proven valuable for visual tracking, as different sensor types offer unique strengths in handling one specific challenging scene where object appearance vari…
Self-Explainable Affordance Learning with Embodied Caption
Zhipeng Zhang, Zhimin Wei, Guolei Sun +2
In the field of visual affordance learning, previous methods mainly used abundant images or videos that delineate human behavior patterns to identify action possibility regions for…
Rethinking Few-shot 3D Point Cloud Semantic Segmentation
Zhaochong An, Guolei Sun, Yun Liu +5
This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS), with a focus on two significant issues in the state-of-the-art: foreground leakage and sparse point dist…
Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation
Zhaochong An, Guolei Sun, Zongwei Wu +2
Modern approaches have proved the huge potential of addressing semantic segmentation as a mask classification task which is widely used in instance-level segmentation. This paradig…
Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image Synthesis
Hao Tang, Guolei Sun, Nicu Sebe +1
We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvements have been achieved by the community in the recent period, the quality…
Object Segmentation by Mining Cross-Modal Semantics
Zongwei Wu, Jingjing Wang, Zhuyun Zhou +5
Multi-sensor clues have shown promise for object segmentation, but inherent noise in each sensor, as well as the calibration error in practice, may bias the segmentation accuracy.…
RGB-D Indiscernible Object Counting in Underwater Scenes
Guolei Sun, Xiaogang Cheng, Zhaochong An +5
Recently, indiscernible/camouflaged scene understanding has attracted lots of research attention in the vision community. We further advance the frontier of this field by systemati…
Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation
Guolei Sun, Yun Liu, Hao Tang +3
The essence of video semantic segmentation (VSS) is how to leverage temporal information for prediction. Previous efforts are mainly devoted to developing new techniques to calcula…
Learning Local and Global Temporal Contexts for Video Semantic Segmentation
Guolei Sun, Yun Liu, Henghui Ding +2
Contextual information plays a core role for video semantic segmentation (VSS). This paper summarizes contexts for VSS in two-fold: local temporal contexts (LTC) which define the c…
SwinIR: Image Restoration Using Swin Transformer
Jingyun Liang, Jiezhang Cao, Guolei Sun +3
Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). Whil…
Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
Jingyun Liang, Guolei Sun, Kai Zhang +2
Existing blind image super-resolution (SR) methods mostly assume blur kernels are spatially invariant across the whole image. However, such an assumption is rarely applicable for r…
Boosting Few-shot Semantic Segmentation with Transformers
Guolei Sun, Yun Liu, Jingyun Liang +1
Due to the fact that fully supervised semantic segmentation methods require sufficient fully-labeled data to work well and can not generalize to unseen classes, few-shot segmentati…
Vision Transformers with Hierarchical Attention
Yun Liu, Yu-Huan Wu, Guolei Sun +3
This paper tackles the high computational/space complexity associated with Multi-Head Self-Attention (MHSA) in vanilla vision transformers. To this end, we propose Hierarchical MHS…
Rethinking Global Context in Crowd Counting
Guolei Sun, Yun Liu, Thomas Probst +3
This paper investigates the role of global context for crowd counting. Specifically, a pure transformer is used to extract features with global information from overlapping image p…
CompositeTasking: Understanding Images by Spatial Composition of Tasks
Nikola Popovic, Danda Pani Paudel, Thomas Probst +2
We define the concept of CompositeTasking as the fusion of multiple, spatially distributed tasks, for various aspects of image understanding. Learning to perform spatially distribu…
LID 2020: The Learning from Imperfect Data Challenge Results
Yunchao Wei, Shuai Zheng, Ming-Ming Cheng +32
Learning from imperfect data becomes an issue in many industrial applications after the research community has made profound progress in supervised learning from perfectly annotate…
Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
Guolei Sun, Wenguan Wang, Jifeng Dai +1
This paper studies the problem of learning semantic segmentation from image-level supervision only. Current popular solutions leverage object localization maps from classifiers as…
Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis
Hao Tang, Xiaojuan Qi, Guolei Sun +4
We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvement has been achieved, the quality of synthesized images is far from satis…
Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes
Guolei Sun, Hisham Cholakkal, Salman Khan +2
The main requisite for fine-grained recognition task is to focus on subtle discriminative details that make the subordinate classes different from each other. We note that existing…
Towards Partial Supervision for Generic Object Counting in Natural Scenes
Hisham Cholakkal, Guolei Sun, Salman Khan +3
Generic object counting in natural scenes is a challenging computer vision problem. Existing approaches either rely on instance-level supervision or absolute count information to t…
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
Syed Waqas Zamir, Aditya Arora, Akshita Gupta +7
Existing Earth Vision datasets are either suitable for semantic segmentation or object detection. In this work, we introduce the first benchmark dataset for instance segmentation i…