Temporal action detection (TAD) aims to detect all action boundaries and...
Significant advancements have been made in multi-object tracking (MOT) w...
Generative models have recently exhibited exceptional capabilities in va...
Existing end-to-end Multi-Object Tracking (e2e-MOT) methods have not
sur...
Recently, the zero-shot semantic segmentation problem has attracted
incr...
Object re-identification (ReID) aims to find instances with the same ide...
In this paper, we present a one-stage framework TriDet for temporal acti...
In person re-identification (ReID) tasks, many works explore the learnin...
Despite recent progress in video and language representation learning, t...
In this paper, we consider the problem of generalised visual object coun...
In this paper, we present a new cross-architecture contrastive learning
...
This work aims at improving instance retrieval with self-supervision. We...
One-stage object detection is commonly implemented by optimizing two
sub...
The conventional detectors tend to make imbalanced classification and su...
Differentiable architecture search is prevalent in the field of NAS beca...
Differentiable architecture search (DAS) has made great progress in sear...
In this paper, we teach machines to understand visuals and natural langu...
Region Proposal Network (RPN) provides strong support for handling the s...
The objective of this work is to learn a compact embedding of a set of
d...
The objective of this paper is to learn a compact representation of imag...