Learning generalizable representation and classifier for class-imbalance...
Cloud-native containerized applications constantly seek high-performance...
Reconstruction-based anomaly detection models achieve their purpose by
s...
The key to address clothes-changing person re-identification (re-id) is ...
The current popular two-stream, two-stage tracking framework extracts th...
Person re-identification (reID) plays an important role in computer visi...
In this paper, we present an efficient spatial-temporal representation f...
This paper proposes a novel model, named Continuity-Discrimination
Convo...
Person re-identification (reID) by CNNs based networks has achieved favo...
This paper proposes a Temporal Complementary Learning Network that extra...
Due to the imperfect person detection results and posture changes, tempo...
Although two-stage object detectors have continuously advanced the
state...
Few-shot classification aims to recognize unlabeled samples from unseen
...
In many scenarios of Person Re-identification (Re-ID), the gallery set
c...
Person re-identification (reID) benefits greatly from deep convolutional...
Video person re-identification (re-ID) plays an important role in
survei...
Recent researches attempt to improve the detection performance by adopti...
This paper presents a review of the 2018 WIDER Challenge on Face and
Ped...
An edge-colored graph G is conflict-free connected if, between each
pair...
Deep learning based methods have recently pushed the state-of-the-art on...
The comparison of heterogeneous samples extensively exists in many
appli...