We introduce VideoPrism, a general-purpose video encoder that tackles diverse video
understanding tasks with a single frozen model. We pretrain VideoPrism on a …

Abstract Video Question Answering (VideoQA) emerges as a prominent trend in the domain
of Artificial Intelligence, Computer Vision, and Natural Language Processing. It involves …

The default strategy for training single-view Large Reconstruction Models (LRMs) follows the
fully supervised route using large-scale datasets of synthetic 3D assets or multi-view …

This study delves into the realm of multi-modality (ie, video and motion modalities) human
behavior understanding by leveraging the powerful capabilities of Large Language Models …

Despite the rapid integration of video perception capabilities into Large Multimodal Models
(LMMs), the underlying mechanisms driving their video understanding remain poorly …

Video captioning is a challenging task and typically requires paired video-text data for
training. However, manually annotating coherent textual descriptions for videos is laborious …

The rapid expansion of multimedia content has made accurately retrieving relevant videos
from large collections increasingly challenging. Recent advancements in text-video retrieval …

To retrieve a video via a multimedia search engine, a textual query is usually created by the
user and then used to perform the search. Recent state-of-the-art cross-modal retrieval …

Video Foundation Models (ViFMs) aim to learn a general-purpose representation for various
video understanding tasks. Leveraging large-scale datasets and powerful models, ViFMs …

Computational approaches leveraging computer vision and machine learning have
transformed the quantification of animal behavior from video. However, existing methods …