Related papers: PG-Video-LLaVA: Pixel Grounding Large Video-Langua…

With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existing works are limited to specialized video understanding…

This paper undertakes an empirical study to revisit the latest advancements in Multimodal Large Language Models (MLLMs): Video Assistant. This study, namely FreeVA, aims to extend existing image-based MLLM to the video domain in a…

Learning to localize temporal boundaries of procedure steps in instructional videos is challenging due to the limited availability of annotated large-scale training videos. Recent works focus on learning the cross-modal alignment between…

Visual Question Answering (VQA) within the surgical domain, utilizing Large Language Models (LLMs), offers a distinct opportunity to improve intra-operative decision-making and facilitate intuitive surgeon-AI interaction. However, the…

With the ever-increasing popularity of pretrained Video-Language Models (VidLMs), there is a pressing need to develop robust evaluation methodologies that delve deeper into their visio-linguistic capabilities. To address this challenge, we…

Video-based large language models (Video-LLMs) have been recently introduced, targeting both fundamental improvements in perception and comprehension, and a diverse range of user inquiries. In pursuit of the ultimate goal of achieving…

With the success of large language models (LLMs), integrating the vision model into LLMs to build vision-language foundation models has gained much more interest recently. However, existing LLM-based large multimodal models (e.g.,…

Visual grounding refers to the ability of a model to identify a region within some visual input that matches a textual description. Consequently, a model equipped with visual grounding capabilities can target a wide range of applications in…

In this paper, we introduce Motion-Grounded Video Reasoning, a new motion understanding task that requires generating visual answers (video segmentation masks) according to the input question, and hence needs implicit spatiotemporal…

Video quality assessment (VQA) is a challenging research topic with broad applications. Traditional hand-crafted and discriminative learning-based VQA models mainly focus on pixel-level distortions and lack contextual understanding, while…

Ensuring accessible pedestrian navigation requires reasoning about both semantic and spatial aspects of complex urban scenes, a challenge that existing Large Vision-Language Models (LVLMs) struggle to meet. Although these models can…

In this work, we tackle the problem of long-form video-language grounding (VLG). Given a long-form video and a natural language query, a model should temporally localize the precise moment that answers the query. Humans can easily solve VLG…

Long-context capability is critical for multi-modal foundation models, especially for long video understanding. We introduce LongVILA, a full-stack solution for long-context visual-language models by co-designing the algorithm and system.…

Large-scale video generative models have shown emerging capabilities as zero-shot visual planners, yet video-generated plans often violate temporal consistency and physical constraints, leading to failures when mapped to executable actions.…

Large language models (LLMs) and large visual language models (LVLMs) have been at the forefront of the artificial intelligence field, particularly for tasks like text generation, video captioning, and question-answering. Typically, it is…

Large vision-and-language models (VLMs) trained to match images with text on large-scale datasets of image-text pairs have shown impressive generalization ability on several vision and language tasks. Several recent works, however, showed…

Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps between common and rare concepts. To…

We introduce LaViLa, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video…

The advent of real-time large multimodal models (LMMs) like GPT-4o has sparked considerable interest in efficient LMMs. LMM frameworks typically encode visual inputs into vision tokens (continuous representations) and integrate them and…

Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, these VLMs are…