Related papers: QuizCram: A Quiz-Driven Lecture Viewing Interface
Video Large Language Models (Video-LLMs) have made remarkable progress in video understanding tasks. However, they are constrained by the maximum length of input tokens, making it impractical to input entire videos. Existing frame selection…
Real-time understanding of continuous video streams is essential for interactive assistants and multimodal agents operating in dynamic environments. However, most existing video reasoning approaches follow a batch paradigm that defers…
In the Fall of 2013, Georgia Tech offered a 'flipped' calculus-based introductory mechanics class as an alternative to the traditional large-enrollment lecture class. This class flipped instruction by introducing new material outside of the…
Visual gaze estimation, with its wide-ranging application scenarios, has garnered increasing attention within the research community. Although existing approaches infer gaze solely from image signals, recent advances in visual-language…
Conversational recommender systems (CRS) aim to provide highquality recommendations in conversations. However, most conventional CRS models mainly focus on the dialogue understanding of the current session, ignoring other rich multi-aspect…
This demo introduces Focus360, a system designed to enhance user engagement in 360{\deg} VR videos by guiding attention to key elements within the scene. Using natural language descriptions, the system identifies important elements and…
The ability to understand long videos is vital for embodied intelligent agents, because their effectiveness depends on how well they can accumulate, organize, and leverage long-horizon perceptual memories. Recently, multimodal LLMs have…
Interdisciplinary studies often require researchers to explore literature in diverse branches of knowledge. Yet, navigating through the highly scattered knowledge from unfamiliar disciplines poses a significant challenge. In this paper, we…
Online design communities, where members exchange free-form views on others' designs, offer a space for beginners to learn visual design. However, the content of these communities is often unorganized for learners, containing many…
State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStruct, a training framework to learn VLMs for effective visual…
Predicting contextualised engagement in videos is a long-standing problem that has been popularly attempted by exploiting the number of views or the associated likes using different computational methods. The recent decade has seen a boom…
Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better…
Despite the number of currently available datasets on video question answering, there still remains a need for a dataset involving multi-step and non-factoid answers. Moreover, relying on video transcripts remains an under-explored topic.…
Streaming video understanding requires models not only to process temporally incoming frames, but also to anticipate user intention for realistic applications such as Augmented Reality (AR) glasses. While prior streaming benchmarks evaluate…
Live streaming, which allows streamers to broadcast their work to live viewers, is an emerging practice for teaching and learning computer programming. Participation in live streaming is growing rapidly, despite several apparent challenges,…
Tutorial videos are a valuable resource for people looking to learn new tasks. People often learn these skills by viewing multiple tutorial videos to get an overall understanding of a task by looking at different approaches to achieve the…
This report presents our solution to the Ego4D Natural Language Queries (NLQ) Challenge at CVPR 2025. Egocentric video captures the scene from the wearer's perspective, where gaze serves as a key non-verbal communication cue that reflects…
Existing e-learning environments primarily focus on the aspect of providing intuitive learning contents and to recommend learning units in a personalized fashion. The major focus of the KnowledgeCheckR environment is to take into account…
Navigating and visualizing multilayered knowledge graphs remains a challenging, unresolved problem in information systems design. Building on our earlier study, which engaged end users in both the design and population of a domain-specific…
In the nascent days of e-content delivery, having a superior product was enough to give companies an edge against the competition. With today's fiercely competitive market, one needs to be multiple steps ahead, especially when it comes to…