In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS),
which aims to segment objects of arbitrary classes instead of pre-defined, closed-set …

Weakly supervised object localization (WSOL) remains challenging when learning object
localization models from image category labels. Conventional methods that discriminatively …

Spatio-temporal video grounding aims to localize the aligned visual tube corresponding to a
language query. Existing techniques achieve such alignment by exploiting dense boundary …

Humans excel at acquiring knowledge through observation. For example, we can learn to
use new tools by watching demonstrations. This skill is fundamental for intelligent systems to …

Abstract Weakly Supervised Object Localization (WSOL), which aims to localize objects by
only using image-level labels, has attracted much attention because of its low annotation …

Weakly supervised object localization and semantic segmentation aim to localize objects
using only image-level labels. Recently, a new paradigm has emerged by generating a …

Referring image segmentation (RIS) aims to localize the object in an image referred by a
natural language expression. Most previous studies learn RIS with a large-scale dataset …

Weakly supervised object localization (WSOL) aims to localize objects based on only image-
level labels as supervision. Recently, transformers have been introduced into WSOL …

Self-supervised vision transformers (SSTs) have shown great potential to yield rich
localization maps that highlight different objects in an image. However, these maps remain …

Obtaining accurate pixel-level localization from class labels is a crucial process in weakly
supervised semantic segmentation and object localization. Attribution maps from a trained …