Related papers: Towards Long-Form Spatio-Temporal Video Grounding
Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on…
We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The…
Efficiently understanding long-form videos remains a significant challenge in computer vision. In this work, we revisit temporal search paradigms for long-form video understanding and address a fundamental issue pertaining to all…
Given an untrimmed video, temporal sentence grounding (TSG) aims to locate a target moment semantically according to a sentence query. Although previous respectable works have made decent success, they only focus on high-level visual…
3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…
Recent advances in video-based multimodal large language models (Video-LLMs) have significantly improved video understanding by processing videos as sequences of image frames. However, many existing methods treat frames independently in the…
A core capability towards general embodied intelligence lies in localizing task-relevant objects from an egocentric perspective, formulated as Spatio-Temporal Video Grounding (STVG). Despite recent progress, existing STVG studies remain…
Spatial and temporal relationships, both short-range and long-range, between objects in videos, are key cues for recognizing actions. It is a challenging problem to model them jointly. In this paper, we first present a new variant of Long…
This paper tackles an emerging and challenging problem of long video temporal grounding~(VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less…
Video Temporal Grounding (VTG) aims to ground specific segments within an untrimmed video corresponding to the given natural language query. Existing VTG methods largely depend on supervised learning and extensive annotated data, which is…
Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art,…
Automatic video captioning is challenging due to the complex interactions in dynamic real scenes. A comprehensive system would ultimately localize and track the objects, actions and interactions present in a video and generate a description…
Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with token count. To address this, we propose a training-free…
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…
Recently, spatiotemporal graphs have emerged as a concise and elegant manner of representing video clips in an object-centric fashion, and have shown to be useful for downstream tasks such as action recognition. In this work, we investigate…
Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a few seconds of video even on high-performance GPUs. This…
Inspired by the performance and scalability of autoregressive large language models (LLMs), transformer-based models have seen recent success in the visual domain. This study investigates a transformer adaptation for video prediction with a…
We introduce TemporalVLM, a video large language model (video LLM) for temporal reasoning and fine-grained understanding in long videos. Our approach includes a visual encoder for mapping a long-term video into features which are time-aware…
Temporal Video Grounding (TVG) aims to localize video segments corresponding to a given textual query, which often describes human actions. However, we observe that current methods, usually optimizing for high temporal…
Most modern approaches in temporal action localization divide this problem into two parts: (i) short-term feature extraction and (ii) long-range temporal boundary localization. Due to the high GPU memory cost caused by processing long…