相关论文: Building Scalable Video Understanding Benchmarks t…
Optimizing large-language model (LLM) training on distributed domain-specific accelerator systems presents significant challenges due to its complex optimization space. Existing optimization methods, however, rely on time-consuming manual…
While the Contrastive Language-Image Pretraining(CLIP) model has achieved remarkable success in a variety of downstream vison language understanding tasks, enhancing its capability for fine-grained image-text alignment remains an active…
Laparoscopic surgery is a complex surgical technique that requires extensive training. Recent advances in deep learning have shown promise in supporting this training by enabling automatic video-based assessment of surgical skills. However,…
Large-scale web-crawled datasets are fundamental for the success of pre-training vision-language models, such as CLIP. However, the inherent noise and potential irrelevance of web-crawled AltTexts pose challenges in achieving precise…
High-quality video datasets are foundational for training robust models in tasks like action recognition, phase detection, and event segmentation. However, many real-world video datasets suffer from annotation errors such as *mislabeling*,…
We propose a semi-supervised learning approach for video classification, VideoSSL, using convolutional neural networks (CNN). Like other computer vision tasks, existing supervised video classification methods demand a large amount of…
This paper presents DriveTrack, a new benchmark and data generation framework for long-range keypoint tracking in real-world videos. DriveTrack is motivated by the observation that the accuracy of state-of-the-art trackers depends strongly…
We propose a rubric-guided, pseudo-labeled, and prompt-driven zero-shot video summarization framework that bridges large language models with structured semantic reasoning. A small subset of human annotations is converted into…
Understanding videos inherently requires reasoning over both visual and auditory information. To properly evaluate Omni-Large Language Models (Omni-LLMs), which are capable of processing multi-modal information including vision and audio,…
The Audio-Visual Video Parsing task aims to identify and temporally localize the events that occur in either or both the audio and visual streams of audible videos. It often performs in a weakly-supervised manner, where only video event…
Videos often have to be transmitted and stored at low bitrates due to poor network connectivity during adaptive bitrate streaming. Designing optimal bitrate ladders that would select the perceptually-optimized resolution, frame-rate, and…
Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow understanding and…
Video Retrieval is a challenging task where a text query is matched to a video or vice versa. Most of the existing approaches for addressing such a problem rely on annotations made by the users. Although simple, this approach is not always…
Automated surgical workflow analysis is crucial for education, research, and clinical decision-making, but the lack of annotated datasets hinders the development of accurate and comprehensive workflow analysis solutions. We introduce a…
Scaling analysis is a technique in computational political science that assigns a political actor (e.g. politician or party) a score on a predefined scale based on a (typically long) body of text (e.g. a parliamentary speech or an election…
We introduce Neptune, a benchmark for long video understanding that requires reasoning over long time horizons and across different modalities. Many existing video datasets and models are focused on short clips (10s-30s). While some long…
Human-centric video frame interpolation has great potential for improving people's entertainment experiences and finding commercial applications in the sports analysis industry, e.g., synthesizing slow-motion videos. Although there are…
We present a new model to determine relative skill from long videos, through learnable temporal attention modules. Skill determination is formulated as a ranking problem, making it suitable for common and generic tasks. However, for long…
Sports video understanding requires perceiving high-speed dynamics, complex rules, and long temporal contexts. Yet, current Multimodal Large Language Models (MLLMs) remain narrowly focused on single sports, specific tasks, or training-free…
Temporal action segmentation is a task to classify each frame in the video with an action label. However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset.…