41 citations · 111 across the 15 of their papers we have counts for
14 papers · 1 filter
Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation
Zicheng Zhang, Tong Zhang, Yi Zhu +4
The pre-trained vision-language model, exemplified by CLIP, advances zero-shot semantic segmentation by aligning visual features with class embeddings through a transformer decoder…
Generalizing Event-Based Motion Deblurring in Real-World Scenarios
Xiang Zhang, Lei Yu, Wen Yang +2
Event-based motion deblurring has shown promising results by exploiting low-latency events. However, current approaches are limited in their practical usage, as they assume the sam…
MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation
Kaixin Cai, Pengzhen Ren, Yi Zhu +5
Recently, semantic segmentation models trained with image-level text supervision have shown promising results in challenging open-world scenarios. However, these models still face…
Video Frame Interpolation with Stereo Event and Intensity Camera
Chao Ding, Mingyuan Lin, Haijian Zhang +2
The stereo event-intensity camera setup is widely applied to leverage the advantages of both event cameras with low latency and intensity cameras that capture accurate brightness a…
Recovering Continuous Scene Dynamics from A Single Blurry Image with Events
Zhangyi Cheng, Xiang Zhang, Lei Yu +3
This paper aims at demystifying a single motion-blurred image with events and revealing temporally continuous scene dynamics encrypted behind motion blurs. To achieve this end, an…
Learning to Super-Resolve Blurry Images with Events
Lei Yu, Bishan Wang, Xiang Zhang +4
Super-Resolution from a single motion Blurred image (SRB) is a severely ill-posed problem due to the joint degradation of motion blurs and low spatial resolution. In this paper, we…
Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation
Bingqian Lin, Yi Zhu, Xiaodan Liang +2
Vision-Language Navigation (VLN) is a challenging task which requires an agent to align complex visual observations to language instructions to reach the goal position. Most existi…
ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency
Pengzhen Ren, Changlin Li, Hang Xu +5
Recently, great success has been made in learning visual representations from text supervision, facilitating the emergence of text-supervised semantic segmentation. However, existi…
CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation
Zicheng Zhang, Yi Zhu, Jianzhuang Liu +2
Referring image segmentation aims at localizing all pixels of the visual objects described by a natural language sentence. Previous works learn to straightforwardly align the sente…
ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts
Bingqian Lin, Yi Zhu, Zicong Chen +3
Vision-Language Navigation (VLN) is a challenging task that requires an embodied agent to perform action-level modality alignment, i.e., make instruction-asked actions sequentially…
Learning Enriched Illuminants for Cross and Single Sensor Color Constancy
Xiaodong Cun, Zhendong Wang, Chi-Man Pun +4
Color constancy aims to restore the constant colors of a scene under different illuminants. However, due to the existence of camera spectral sensitivity, the network trained on a c…
Motion Deblurring with Real Events
Fang Xu, Lei Yu, Bishan Wang +5
In this paper, we propose an end-to-end learning framework for event-based motion deblurring in a self-supervised manner, where real-world events are exploited to alleviate the per…
Multi-Target Domain Adaptation with Collaborative Consistency Learning
Takashi Isobe, Xu Jia, Shuaijun Chen +5
Recently unsupervised domain adaptation for the semantic segmentation task has become more and more popular due to high-cost of pixel-level annotation on real-world images. However…
Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
Jianzhong He, Xu Jia, Shuaijun Chen +1
Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a nov…