12 accepted papers
Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) trans…
The recently proposed SparseFormer architecture provides an alternative approach to visual understanding by utilizing a significantly lower number of visual tokens via adjusting RoIs greatly reducing computational costs while still achieving promising performance. However training SparseFormers from…
We present Ego-Exo4D a diverse large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g. sports music dance bike repair). 740 participants from 13 cities worldwide perform…
"Narrative videos, such as movies, pose significant challenges in video understanding due to their rich contexts (characters, dialogues, storylines) and diverse demands (identify who [?], relationship [?], and reason [?]). In this paper, we introduce , a multimodal language model developed to addres…
We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. Leveraging the reasoning capabilities and world knowledge of large language models, and augmented by the Segment Anything Model, VideoLISA gen…
A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially in long-term, dense video frame streaming scenarios. Althoug…
Large Language Models (LLMs) have been enhanced with vision capabilities enabling them to comprehend images videos and interleaved vision-language content. However the learning methods of these large multimodal models (LMMs) typically treat videos as predetermined clips rendering them less effective…
Humans excel at learning from expert demonstrations and solving their own problems. To equip intelligent robots and assistants, such as AR glasses, with this ability, it is essential to ground human hand interactions (i.e., affordances) from demonstration videos and apply them to a target image like…
A standard hardware bottleneck when training deep neural networks is GPU memory. The bulk of memory is occupied by caching intermediate tensors for gradient computation in the backward pass. We propose a novel method to reduce this footprint - Dropping Intermediate Tensors (DropIT). DropIT drops mi…
The usage of exocentric and egocentric videos in Video Question Answering (VQA) is a new endeavor in human-robot interaction and collaboration studies. Particularly for egocentric videos, one may leverage eye-gaze information to understand human intentions during the task. In this paper, we build a…
Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most methods in this direction develop task-specific models that…
"A long-standing goal of intelligent assistants such as AR glasses/robots has been to assist users in affordance-centric real-world scenarios, such as ""how can I run the microwave for 1 minute?”. However, there is still no clear task definition and suitable benchmarks. In this paper, we define a ne…