A new trend in the computer vision community is to capture objects of
in...
Recently 3D object detection from surround-view images has made notable
...
Referring video object segmentation (RVOS) aims at segmenting an object ...
We present the 1st-place solution of OpenLane Topology in Autonomous Dri...
Although end-to-end multi-object trackers like MOTR enjoy the merits of
...
In this paper, we propose a long-sequence modeling framework, named
Stre...
Existing referring understanding tasks tend to involve the detection of ...
In this paper, we propose a robust 3D detector, named Cross Modal Transf...
In this paper, we propose MOTRv2, a simple yet effective pipeline to
boo...
We present our 1st place solution to the Group Dance Multiple People Tra...
In this paper, we propose PETRv2, a unified framework for 3D perception ...
Sparsely annotated semantic segmentation (SASS) aims to train a segmenta...
In this paper, we develop position embedding transformation (PETR) for
m...
We propose a novel implicit feature refinement module for high-quality
i...
In this paper, we propose an end-to-end framework for instance segmentat...
The key challenge in multiple-object tracking (MOT) task is temporal mod...
In this paper, we present an implicit feature pyramid network (i-FPN) fo...
Object detectors usually achieve promising results with the supervision ...
Despite the previous success of object analysis, detecting and segmentin...
Understanding interactions between humans and objects is one of the
fund...
Human-object interaction detection is an important and relatively new cl...