相关论文: Video-in-the-Loop: Span-Grounded Long Video QA wit…
We introduce VideoComp, a benchmark and learning framework for advancing video-text compositionality understanding, aimed at improving vision-language models (VLMs) in fine-grained temporal alignment. Unlike existing benchmarks focused on…
The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks. Long-term temporal reasoning is a key desideratum for frame retrieval systems.…
Many video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames. Existing methods built on large vision-language models (LVLMs) often address this challenge by externalizing reasoning through…
Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual…
Vision-language large models have achieved remarkable success in various multi-modal tasks, yet applying them to video understanding remains challenging due to the inherent complexity and computational demands of video data. While…
Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models,…
We present Q-ViD, a simple approach for video question answering (video QA), that unlike prior methods, which are based on complex architectures, computationally expensive pipelines or use closed models like GPTs, Q-ViD relies on a single…
In recent years, video question answering based on multimodal large language models (MLLM) has garnered considerable attention, due to the benefits from the substantial advancements in LLMs. However, these models have a notable deficiency…
Training models with longer in-context lengths is a significant challenge for multimodal model due to substantial GPU memory and computational costs. This exploratory study does not present state-of-the-art models; rather, it introduces an…
Video Temporal Grounding (VTG) aims to localize relevant temporal segments in videos given natural language queries. Despite recent progress with large vision-language models (LVLMs) and instruction-tuning, existing approaches often suffer…
Video Large Language Models (Video LLMs) achieve strong performance on video understanding tasks but suffer from high inference costs due to the large number of visual tokens. We propose KiToke, a training-free, query-agnostic token…
Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. Following the human perception process, where the scene is effectively understood…
Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quality video data. This paper addresses the challenge by…
This work presents VTok, a unified video tokenization framework that can be used for both generation and understanding tasks. Unlike the leading vision-language systems that tokenize videos through a naive frame-sampling strategy, we…
In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual…
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…
Multimodal large language models (MLLMs) have demonstrated remarkable potential for enhancing scene understanding in autonomous driving systems through powerful logical reasoning capabilities. However, the deployment of these models faces…
Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to supervising VLAs with latent actions are fragmented and…
Video summarization aims to create short, accurate, and cohesive summaries of longer videos. Despite the existence of various video summarization datasets, a notable limitation is their limited amount of source videos, which hampers the…
Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style process misaligned with real-world video streams where…