One-to-one set matching is a key design for DETR to establish its end-to-end capability, so
that object detection does not require a hand-crafted NMS (non-maximum suppression) to …

In this paper, we propose MOTRv2, a simple yet effective pipeline to bootstrap end-to-end
multi-object tracking with a pretrained object detector. Existing end-to-end methods, eg …

This work presents a simple vision transformer design as a strong baseline for object
localization and instance segmentation tasks. Transformers recently demonstrate …

Referring video object segmentation (R-VOS) is an emerging cross-modal task that aims to
segment the target object referred by a language expression in all video frames. In this work …

Temporal action detection (TAD) aims to determine the semantic label and the temporal
interval of every action instance in an untrimmed video. It is a fundamental and challenging …

We propose MinVIS, a minimal video instance segmentation (VIS) framework that achieves
state-of-the-art VIS performance with neither video-based architectures nor training …

We introduce a novel paradigm for offline Video Instance Segmentation (VIS), based on the
hypothesis that explicit object-oriented information can be a strong clue for understanding …

Abstract Referring Video Object Segmentation (RVOS) is to segment the object instance
from a given video, according to the textual description of this object. However, in the open …

Referring video object segmentation aims to segment a referent throughout a video
sequence according to a natural language expression. It requires aligning the natural …

Abstract Existing Video Object Segmentation (VOS) relies on explicit user instructions, such
as categories, masks, or short phrases, restricting their ability to perform complex video …