Spatiotemporal prediction aims to generate future sequences by paradigms...
Existing knowledge distillation works for semantic segmentation mainly f...
Extracting class activation maps (CAM) is a key step for weakly-supervis...
Face clustering is a promising way to scale up face recognition systems ...
Since Intersection-over-Union (IoU) based optimization maintains the
con...
Weakly supervised object detection (WSOD), which is an effective way to ...
Structural re-parameterization has drawn increasing attention in various...
Monocular 3D object detection is an essential task in autonomous driving...
The application of cross-dataset training in object detection tasks is
c...
Click-through rate(CTR) prediction is a core task in cost-per-click(CPC)...
We focus on the confounding bias between language and location in the vi...
Graph Neural Networks (GNNs) have become increasingly popular and achiev...
Unsupervised Person Re-identification (U-ReID) with pseudo labeling rece...
A good visual representation is an inference map from observations (imag...
Finding a suitable density function is essential for density-based clust...
A networked time series (NETS) is a family of time series on a given gra...
We propose a novel and flexible roof modeling approach that can be used ...
Temporal relational data, perhaps the most commonly used data type in
in...
Though 3D object detection from point clouds has achieved rapid progress...
Current geometry-based monocular 3D object detection models can efficien...
Knowledge Distillation (KD) is a popular technique to transfer knowledge...
Click-through rate (CTR) prediction plays an important role in online
ad...
With the increasing scale and diversification of interaction behaviors i...
Recently, people tried to use a few anomalies for video anomaly detectio...
Recently, some contrastive learning methods have been proposed to
simult...
Despite their success for semantic segmentation, convolutional neural
ne...
Cloth-Changing person re-identification (CC-ReID) aims at matching the s...
Weakly-supervised Temporal Action Localization (WTAL) aims to detect the...
Video-based person re-identification (re-ID) aims at matching the same p...
With the magnitude of graph-structured data continually increasing, grap...
This paper tackles the purely unsupervised person re-identification (Re-...
Model efficiency is crucial for object detection. Mostprevious works rel...
Skeleton-based human action recognition has attracted much attention wit...
Binary grid mask representation is broadly used in instance segmentation...
Multi-object tracking (MOT) has always been a very important research
di...
Recently, hashing is widely-used in approximate nearest neighbor search ...
As the class size grows, maintaining a balanced dataset across many clas...
Today, scene graph generation(SGG) task is largely limited in realistic
...
With the rise of deep learning methods, person Re-Identification (ReID)
...
How to learn a stable model under agnostic distribution shift between
tr...
Due to the advanced capabilities of the Internet of Vehicles (IoV) compo...
Coupled with the rise of Deep Learning, the wealth of data and enhanced
...
Optimization techniques are of great importance to effectively and
effic...
We present a novel unsupervised feature representation learning method,
...
Today's scene graph generation (SGG) task is still far from practical, m...
Intra-camera supervision (ICS) for person re-identification (Re-ID) assu...
This paper is a winner report from team MReaL-BDAI for Visual Dialog
Cha...
Although deep neural networks are highly effective, their high computati...
Model fine-tuning is a widely used transfer learning approach in person
...
Personalized news recommendation is very important for online news platf...