Related papers: How Much Temporal Long-Term Context is Needed for …
Temporal Action Localization (TAL) is a challenging task in video understanding that aims to identify and localize actions within a video sequence. Recent studies have emphasized the importance of applying long-term temporal context…
Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due to the context length constraint of LLMs and the vast…
Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an…
Temporal context plays a significant role in temporal action segmentation. In an offline setting, the context is typically captured by the segmentation network after observing the entire sequence. However, capturing and using such context…
Video segmentation encompasses a wide range of categories of problem formulation, e.g., object, scene, actor-action and multimodal video segmentation, for delineating task-specific scene components with pixel-level masks. Recently,…
While most modern video understanding models operate on short-range clips, real-world videos are often several minutes long with semantically consistent segments of variable length. A common approach to process long videos is applying a…
This paper proposes a method for long-term action anticipation (LTA), the task of predicting action labels and their duration in a video given the observation of an initial untrimmed video interval. We build on an encoder-decoder…
We propose an action parsing algorithm to parse a video sequence containing an unknown number of actions into its action segments. We argue that context information, particularly the temporal information about other actions in the video…
Our world offers a never-ending stream of visual stimuli, yet today's vision systems only accurately recognize patterns within a few seconds. These systems understand the present, but fail to contextualize it in past or future events. In…
Temporally locating and classifying action segments in long untrimmed videos is of particular interest to many applications like surveillance and robotics. While traditional approaches follow a two-step pipeline, by generating frame-wise…
In video analysis, understanding the temporal context is crucial for recognizing object interactions, event patterns, and contextual changes over time. The proposed model leverages adjacency and semantic similarities between objects from…
In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance. To incorporate the…
Future prediction, especially in long-range videos, requires reasoning from current and past observations. In this work, we address questions of temporal extent, scaling, and level of semantic abstraction with a flexible multi-granular…
In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and semantic segmentation. For action recognition, I have…
This work focuses on anticipating long-term human actions, particularly using short video segments, which can speed up editing workflows through improved suggestions while fostering creativity by suggesting narratives. To this end, we imbue…
Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized…
Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are…
Deep convolutional networks have achieved great success for visual recognition in still images. However, for action recognition in videos, the advantage over traditional methods is not so evident. This paper aims to discover the principles…
The ability to choose an appropriate camera view among multiple cameras plays a vital role in TV shows delivery. But it is hard to figure out the statistical pattern and apply intelligent processing due to the lack of high-quality training…
Despite recent advances in Vision-Language Models (VLMs), long-video understanding remains a challenging problem. Although state-of-the-art long-context VLMs can process around 1000 input frames, they still struggle to effectively leverage…