Related papers: Decoupling Static and Hierarchical Motion Percepti…
Common-sense physical reasoning in the real world requires learning about the interactions of objects and their dynamics. The notion of an abstract object, however, encompasses a wide variety of physical objects that differ greatly in terms…
Conventional video object segmentation (VOS) methods usually necessitate a substantial volume of pixel-level annotated video data for fully supervised learning. In this paper, we present HVC, a \textbf{h}ybrid static-dynamic \textbf{v}isual…
Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video…
Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video. We propose a novel region-based multiscale spatiotemporal saliency detection method for videos, where static features and…
In this paper, we consider the task of unsupervised object discovery in videos. Previous works have shown promising results via processing optical flows to segment objects. However, taking flow as input brings about two drawbacks. First,…
Video recognition remains an open challenge, requiring the identification of diverse content categories within videos. Mainstream approaches often perform flat classification, overlooking the intrinsic hierarchical structure relating…
It is not always possible to recognise objects and infer material properties for a scene from visual cues alone, since objects can look visually similar whilst being made of very different materials. In this paper, we therefore present an…
Actor-action semantic segmentation made an important step toward advanced video understanding problems: what action is happening; who is performing the action; and where is the action in space-time. Current models for this problem are…
This paper addresses the task of unsupervised video multi-object segmentation. Current approaches follow a two-stage paradigm: 1) detect object proposals using pre-trained Mask R-CNN, and 2) conduct generic feature matching for temporal…
Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on large-scale datasets. To…
In this paper, we present a novel perceptual consistency perspective on video semantic segmentation, which can capture both temporal consistency and pixel-wise correctness. Given two nearby video frames, perceptual consistency measures how…
Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods…
Detecting human-object interactions (HOI) is an important step toward a comprehensive visual understanding of machines. While detecting non-temporal HOIs (e.g., sitting on a chair) from static images is feasible, it is unlikely even for…
An important aspect of video understanding is the ability to predict the evolution of its content in the future. This paper presents a future frame semantic segmentation technique for predicting semantic masks of the current and future…
While generic object detection has achieved large improvements with rich feature hierarchies from deep nets, detecting small objects with poor visual cues remains challenging. Motion cues from multiple frames may be more informative for…
Recent advances in deep learning have brought significant progress in visual grounding tasks such as language-guided video object segmentation. However, collecting large datasets for these tasks is expensive in terms of annotation time,…
This fourth and last tome is focusing on describing the envisioned works for a project that has been presented in the preceding tome. It is about a new approach dedicated to the coding of still and moving pictures, trying to bridge the…
Referring Image Segmentation (RIS) requires identifying objects from images based on textual descriptions. We observe that existing methods significantly underperform on motion-related queries compared to appearance-based ones. To address…
We present REM, a framework for segmenting a wide range of concepts in video that can be described through natural language. Our method leverages the universal visual-language mapping learned by video diffusion models on Internet-scale data…
Video segmentation is a stepping stone to understanding video context. Video segmentation enables one to represent a video by decomposing it into coherent regions which comprise whole or parts of objects. However, the challenge originates…