K
Kaiyang Zhou
Researcher at University of Surrey
Publications - 41
Citations - 2634
Kaiyang Zhou is an academic researcher from University of Surrey. The author has contributed to research in topics: Computer science & Domain (software engineering). The author has an hindex of 14, co-authored 26 publications receiving 1001 citations. Previous affiliations of Kaiyang Zhou include Nanyang Technological University & Queen Mary University of London.
Papers
More filters
Proceedings ArticleDOI
Omni-Scale Feature Learning for Person Re-Identification
TL;DR: Zhou et al. as mentioned in this paper designed a residual block composed of multiple convolutional feature streams, each detecting features at a certain scale, and a novel unified aggregation gate was introduced to dynamically fuse multi-scale features with input-dependent channel-wise weights.
Posted Content
Omni-Scale Feature Learning for Person Re-Identification
TL;DR: A novel deep ReID CNN is designed, termed Omni-Scale Network (OSNet), for omni-scale feature learning by designing a residual block composed of multiple convolutional feature streams, each detecting features at a certain scale.
Proceedings ArticleDOI
Conditional Prompt Learning for Vision-Language Models
TL;DR: Conditional Context Optimization (CoCoOp), which extends CoOp by further learning a lightweight neural network to generate for each image an input-conditional token (vector), and yields stronger domain generalization performance as well.
Posted Content
Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward
Kaiyang Zhou,Yu Qiao,Tao Xiang +2 more
TL;DR: In this article, a deep summarization network (DSN) is proposed to generate more diverse and representative video summaries, which does not rely on labels or user interactions at all.
Journal ArticleDOI
Deep Domain-Adversarial Image Generation for Domain Generalisation
TL;DR: This paper proposes a novel DG approach based on Deep Domain-Adversarial Image Generation based on augmenting the source training data with the generated unseen domain data to make the label classifier more robust to unknown domain changes.