The visual models pretrained on large-scale benchmarks encode general
kn...
Anomaly detection (AD), aiming to find samples that deviate from the tra...
Generating realistic human motion from given action descriptions has
exp...
Photos serve as a way for humans to record what they experience in their...
DETR has set up a simple end-to-end pipeline for object detection by
for...
Object detection on drone images with low-latency is an important but
ch...
Realistic face rendering from multi-view images is beneficial to various...
A key challenge for LiDAR-based 3D object detection is to capture suffic...
Inspired by recent advances in diffusion models, which are reminiscent o...
Planar grasp detection is one of the most fundamental tasks to robotic
m...
We propose a new method for object pose estimation without CAD models. T...
We propose a novel approach to self-supervised learning of point cloud
r...
In this paper, we focus on the problem of feature learning in the presen...
Along with the widespread use of face recognition systems, their
vulnera...
This paper presents an approach that reconstructs a hand-held object fro...
Learning accurate depth is essential to multi-view 3D object detection.
...
Contrastive learning has shown great potential in video representation
l...
Video Anomaly Detection (VAD) is an important topic in computer vision.
...
Active learning is a promising alternative to alleviate the issue of hig...
Domain adaptive object detection (DAOD) is a promising way to alleviate
...
In autonomous driving, LiDAR point-clouds and RGB images are two major d...
Precise representations of 3D faces are beneficial to various computer v...
Weakly-supervised temporal action localization (WTAL) in untrimmed video...
This paper proposes a novel approach to object detection on drone imager...
Occlusions are very common in face images in the wild, leading to the
de...
The recent studies on semantic segmentation are starting to notice the
s...
Action detection plays an important role in high-level video understandi...
Differentiable ARchiTecture Search (DARTS) uses a continuous relaxation ...
RGB-D based 6D pose estimation has recently achieved remarkable progress...
Deep generative approaches have recently made considerable progress in i...
The widespread adoption of online social networks in daily life has crea...
This paper proposes a new deep learning approach to antipodal grasp
dete...
Although much progress has been made recently in 3D face reconstruction,...
The existing auto-encoder based face pose editing methods primarily focu...
In this paper, an effective pipeline to automatic 4D Facial Expression
R...
Anomaly detection is a challenging task and usually formulated as an
uns...
Objects in aerial images usually have arbitrary orientations and are den...
LiDAR-based 3D object detection is an important task for autonomous driv...
Few-shot object detection (FSOD) helps detectors adapt to unseen classes...
We study how to leverage Web images to augment human-curated object dete...
Recent years have witnessed great progress in deep learning based object...
Winograd's minimal filtering algorithm has been widely used in Convoluti...
Recently, Human Attribute Recognition (HAR) has become a hot topic due t...
Performing controlled experiments on noisy data is essential in thorough...
Pyramidal feature representation is the common practice to address the
c...
Recent emerged quantization technique (i.e., using low bit-width fixed-p...
Automation engineering is the task of integrating, via software, various...
Representation learning on graphs has been gaining attention due to its ...
Graph embedding is the task of representing nodes of a graph in a
low-di...
Simulating and predicting planetary-scale techno-social systems poses he...