As the most fundamental scene understanding tasks, object detection and segmentation
have made tremendous progress in deep learning era. Due to the expensive manual …

This paper studies the problem of weakly open-vocabulary semantic segmentation
(WOVSS), which learns to segment objects of arbitrary classes using mere image-text pairs …

This paper proposes LLaFS the first attempt to leverage large language models (LLMs) in
few-shot segmentation. In contrast to the conventional few-shot segmentation methods that …

Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the
impressive performance. However, their expensive computation costs, ie, throughput and …

Open-vocabulary (OV) semantic segmentation has attracted increasing attention in recent
years, which aims to recognize objects in an open class set for real-world applications …

Recent works on open-vocabulary 3D instance segmentation show strong promise, but at
the cost of slow inference speed and high computation requirements. This high computation …

Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the
impressive performance. However, their expensive computation costs, ie, throughput and …

Panoramic images, capturing a 360 {\deg} field of view (FoV), encompass omnidirectional
spatial information crucial for scene understanding. However, it is not only costly to obtain …

As one of the fundamental video tasks in computer vision, Open-Vocabulary Action
Recognition (OVAR) recently gains increasing attention, with the development of vision …

We formally define a novel valuable information retrieval task: image-to-multi-modal-retrieval
(IMMR), where the query is an image and the doc is an entity with both image and textual …