Due to the difficulty in scaling up, generative adversarial networks (GA...
Prompt tuning and adapter tuning have shown great potential in transferr...
Despite the rapid advance of 3D-aware image synthesis, existing studies
...
Semantically coherent out-of-distribution (SCOOD) detection aims to disc...
Human brains respond to semantic features of presented stimuli with diff...
This work presents two astonishing findings on neural networks learned f...
The rank of neural networks measures information flowing across layers. ...
Human can extrapolate well, generalize daily knowledge into unseen scena...
MLP-like models built entirely upon multi-layer perceptrons have recentl...
RGB-infrared person re-identification is an emerging cross-modality
re-i...
Generalizable person re-identification aims to learn a model with only
s...
Existing person re-identification (ReID) methods typically directly load...
Existing disentangled-based methods for generalizable person
re-identifi...
Existing person re-identification (re-id) methods are stuck when deploye...
Occluded person re-identification (ReID) aims to match person images wit...
Although existing person re-identification (Re-ID) methods have shown
im...
Video-based person re-identification aims to match pedestrians from vide...
Cross-modal video-text retrieval, a challenging task in the field of vis...
Cloth-Changing person re-identification (CC-ReID) aims at matching the s...
Unsupervised domain adaptive (UDA) person re-identification (ReID) aims ...
Unsupervised Domain Adaptive (UDA) person re-identification (ReID) aims ...
Many unsupervised domain adaptive (UDA) person re-identification (ReID)
...
Existing dominant approaches for cross-modal video-text retrieval task a...
Abstraction reasoning is a long-standing challenge in artificial
intelli...