相关论文: Augmenting Sports Videos with VisCommentator
Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve. We present a new framework to facilitate bounding box annotations…
Sports have long attracted broad attention as they push the limits of human physical and cognitive capabilities. Amid growing interest in spatial intelligence for vision-language models (VLMs), sports provide a natural testbed for…
Recent progress in computer vision has produced a wide range of powerful specialized models for detection, segmentation, counting, and other visual tasks. However, these models are usually optimized for isolated task formulations, making it…
While esports organizations are increasingly adopting practices of conventional sports teams, such as dedicated analysts and data-driven decision-making, video-based game review is still the primary mode of game analysis. In conventional…
State-of-the-art video action classifiers often suffer from overfitting. They tend to be biased towards specific objects and scene cues, rather than the foreground action content, leading to sub-optimal generalization performances. Recent…
The recognition of human activities is one of the key problems in video understanding. Action recognition is challenging even for specific categories of videos, such as sports, that contain only a small set of actions. Interestingly, sports…
As online news increasingly include data journalism, there is a corresponding increase in the incorporation of visualization in article thumbnail images. However, little research exists on the design rationale for visualization thumbnails,…
Detecting players from sports broadcast videos is essential for intelligent event analysis. However, existing methods assume fixed player categories, incapably accommodating the real-world scenarios where categories continue to evolve.…
Multimodal large language models (MLLMs) excel at general video understanding but struggle with fast, high-frequency sports like tennis, where rally clips are short yet information-dense. To systematically evaluate MLLMs in this challenging…
The massive growth of sports videos has resulted in a need for automatic generation of sports highlights that are comparable in quality to the hand-edited highlights produced by broadcasters such as ESPN. Unlike previous works that mostly…
Sports analytics has been an up-and-coming field of research among professional sporting organizations and academic institutions alike. With the insurgence and collection of athlete data, the primary goal of such analysis is to improve…
Generating natural language descriptions for videos, i.e., video captioning, essentially requires step-by-step reasoning along the generation process. For example, to generate the sentence "a man is shooting a basketball", we need to first…
Watching a 360{\deg} sports video requires a viewer to continuously select a viewing angle, either through a sequence of mouse clicks or head movements. To relieve the viewer from this "360 piloting" task, we propose "deep 360 pilot" -- a…
Sports analysis has gained paramount importance for coaches, scouts, and fans. Recently, computer vision researchers have taken on the challenge of collecting the necessary data by proposing several methods of automatic player and ball…
Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employing GPT-based agents have emerged as promising solutions.…
In this data-rich era of astronomy, there is a growing reliance on automated techniques to discover new knowledge. The role of the astronomer may change from being a discoverer to being a confirmer. But what do astronomers actually look at…
Considering the importance of building a good Visual Dialog (VD) Questioner, many researchers study the topic under a Q-Bot-A-Bot image-guessing game setting, where the Questioner needs to raise a series of questions to collect information…
Understanding broadcast videos is a challenging task in computer vision, as it requires generic reasoning capabilities to appreciate the content offered by the video editing. In this work, we propose SoccerNet-v2, a novel large-scale corpus…
Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors…
Captions that describe or explain charts help improve recall and comprehension of the depicted data and provide a more accessible medium for people with visual disabilities. However, current approaches for automatically generating such…