Related papers: Towards Long Form Audio-visual Video Understanding
In this work, we introduce long-video masked-embedding autoencoders (LV-MAE), a self-supervised learning framework for long video representation. Our approach treats short- and long-span dependencies as two separate tasks. Such decoupling…
Long video understanding presents challenges due to the inherent high computational complexity and redundant temporal information. An effective representation for long videos must efficiently process such redundancy while preserving…
We introduce Activity Graph Transformer, an end-to-end learnable model for temporal action localization, that receives a video as input and directly predicts a set of action instances that appear in the video. Detecting and localizing…
This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for video understanding, that capably understands arbitrary-length video with a constant number of video tokens streamingly encoded and adaptively selected.…
Background: The classroom discourse analysis has been transformed by the growing use of audio-video multimodal data, which demands analytical methods that balance interpretive depth with computational scalability. Methods: This study…
Long-form video understanding poses a significant challenge for video large language models (VideoLLMs) due to prohibitively high computational and memory demands. In this paper, we propose FlexSelect, a flexible and efficient token…
Large multimodal models (LMMs) excel in scene understanding but struggle with fine-grained spatiotemporal reasoning due to weak alignment between linguistic and visual representations. Existing methods map textual positions and durations…
This paper studies the task of temporal moment localization in a long untrimmed video using natural language query. Given a query sentence, the goal is to determine the start and end of the relevant segment within the video. Our key…
This paper introduces InternVid, a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations for multimodal understanding and generation. The InternVid dataset contains over 7…
Given a video with aligned dialogue, people can often infer what is more likely to happen next. Making such predictions requires not only a deep understanding of the rich dynamics underlying the video and dialogue, but also a significant…
Sound event localization and detection with source distance estimation (3D SELD) involves not only identifying the sound category and its direction-of-arrival (DOA) but also predicting the source's distance, aiming to provide full…
Complex activities in real-world audio unfold over extended durations and exhibit hierarchical structure, yet most prior work focuses on short clips and isolated events. To bridge this gap, we introduce MultiAct, a new dataset and benchmark…
Audio-Visual Video Parsing (AVVP) task aims to parse the event categories and occurrence times from audio and visual modalities in a given video. Existing methods usually focus on implicitly modeling audio and visual features through weak…
Video anomaly detection under video-level labels is currently a challenging task. Previous works have made progresses on discriminating whether a video sequencecontains anomalies. However, most of them fail to accurately localize the…
We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots. Casting the problem as a structured prediction problem on sequential data, our main idea is to use Long Short-Term…
This paper addresses the problem of how to exploit spatio-temporal information available in videos to improve the object detection precision. We propose a two stage object detector called FANet based on short-term spatio-temporal feature…
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without…
Properly evaluating the ability of Video-Language Models (VLMs) to understand long videos remains a challenge. We propose a long-context video understanding benchmark, Causal2Needles, that assesses two crucial abilities insufficiently…
Most natural videos contain numerous events. For example, in a video of a "man playing a piano", the video might also contain "another man dancing" or "a crowd clapping". We introduce the task of dense-captioning events, which involves both…
Long video question answering (Long-Video QA) increasingly relies on agentic tool use to retrieve evidence from long videos. In realistic settings, this process often requires multi-hop retrieval, where agents must iteratively gather…