2 citations · 5 across the 33 of their papers we have counts for
33 papers · 1 filter
Incentivizing Vision Language Models to Search for Long Video Question Answering
Harsh Goel, S P Sharan, Sahil Shah +4
We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-turn retrieval process. VSeek…
EgoExo-WM: Unlocking Exo Video for Ego World Models
Danny Tran, Roberto Martín-Martín, Kristen Grauman
Egocentric world models present a promising direction for enabling agents to predict and plan, but their performance is constrained by the limited availability of egocentric traini…
Personal Visual Context Learning in Large Multimodal Models
Zihui Xue, Ami Baid, Sangho Kim +2
As wearable devices like smart glasses integrate Large Multimodal Models (LMMs) into the continuous first-person visual streams of individual users, the evolution of these models i…
Materialistic RIR: Material Conditioned Realistic RIR Generation
Mahnoor Fatima Saad, Sagnik Majumder, Kristen Grauman +1
Rings like gold, thuds like wood! The sound we hear in a scene is shaped not only by the spatial layout of the environment but also by the materials of the objects and surfaces wit…
UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding
Joungbin An, Agrim Jain, Kristen Grauman
Video temporal grounding (VTG) is typically tackled with dataset-specific models that transfer poorly across domains and query styles. Recent efforts to overcome this limitation ha…
Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models
Ami Baid, Zihui Xue, Kristen Grauman
While Audio-Visual Language Models (AVLMs) have achieved remarkable progress over recent years, their reliability is bottlenecked by cross-modal hallucination. A particularly perva…
ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos
Arjun Somayazulu, Kristen Grauman
Visual feedback is critical for motor skill acquisition in sports and rehabilitation, and psychological studies show that observing near-perfect versions of one's own performance a…
SportSkills: Physical Skill Learning from Sports Instructional Videos
Kumar Ashutosh, Chi Hsuan Wu, Kristen Grauman
Current large-scale video datasets focus on general human activity, but lack depth of coverage on fine-grained activities needed to address physical skill learning. We introduce Sp…
MistExit: Learning to Exit for Early Mistake Detection in Procedural Videos
Sagnik Majumder, Anish Nethi, Ziad Al-Halah +1
We introduce the task of early mistake detection in video, where the goal is to determine whether a keystep in a procedural activity is performed correctly while observing as littl…
Human detectors are surprisingly powerful reward models
Kumar Ashutosh, XuDong Wang, Xi Yin +4
Video generation models have recently achieved impressive visual fidelity and temporal coherence. Yet, they continue to struggle with complex, non-rigid motions, especially when sy…
Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video
Daniel Adebi, Sagnik Majumder, Kristen Grauman
Understanding camera motion is a fundamental problem in embodied perception and 3D scene understanding. While visual methods have advanced rapidly, they often struggle under visual…
Learning Skill-Attributes for Transferable Assessment in Video
Kumar Ashutosh, Kristen Grauman
Skill assessment from video entails rating the quality of a person's physical performance and explaining what could be done better. Today's models specialize for an individual spor…
Seeing without Pixels: Perception from Camera Trajectories
Zihui Xue, Kristen Grauman, Dima Damen +2
Can one perceive a video's content without seeing its pixels, just from the camera trajectory-the path it carves through space? This paper is the first to systematically investigat…
SkillSight: Efficient First-Person Skill Assessment with Gaze
Chi Hsuan Wu, Kumar Ashutosh, Kristen Grauman
Egocentric perception on smart glasses could transform how we learn new skills in the physical world, but automatic skill assessment remains a fundamental technical challenge. We i…
When Thinking Drifts: Evidential Grounding for Robust Video Reasoning
Mi Luo, Zihui Xue, Alex Dimakis +1
Video reasoning, the task of enabling machines to infer from dynamic visual content through multi-step logic, is crucial for advanced AI. While the Chain-of-Thought (CoT) mechanism…
Seeing the Arrow of Time in Large Multimodal Models
Zihui Xue, Mi Luo, Kristen Grauman
The Arrow of Time (AoT)-time's irreversible flow shaping physical events-is fundamental to video comprehension, yet remains a significant challenge for modern large multimodal mode…
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
Jang Hyun Cho, Andrea Madotto, Effrosyni Mavroudi +26
Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The researc…
ViewBridge: Curriculum Knowledge Distillation for Activity View-Invariance Under Extreme Viewpoint Changes
Arjun Somayazulu, Efi Mavroudi, Changan Chen +2
Traditional methods for view-invariant learning rely on controlled multi-view training data with minimal scene clutter. However, they struggle with in-the-wild videos that exhibit…
Stitch-a-Demo: Video Demonstrations from Multistep Descriptions
Chi Hsuan Wu, Kumar Ashutosh, Kristen Grauman
When obtaining visual illustrations from text descriptions, today's methods take a description with a single text context - a caption, or an action description - and retrieve or ge…
SPOC: Spatially-Progressing Object State Change Segmentation in Video
Priyanka Mandikal, Tushar Nagarajan, Alex Stoken +2
Object state changes in video reveal critical cues about human and agent activity. However, existing methods are limited to temporal localization of when the object is in its initi…
Switch-a-View: View Selection Learned from Unlabeled In-the-wild Videos
Sagnik Majumder, Tushar Nagarajan, Ziad Al-Halah +1
We introduce SWITCH-A-VIEW, a model that learns to automatically select the viewpoint to display at each timepoint when creating a how-to video. The key insight of our approach is…
Progress-Aware Video Frame Captioning
Zihui Xue, Joungbin An, Xitong Yang +1
While image captioning provides isolated descriptions for individual images, and video captioning offers one single narrative for an entire video clip, our work explores an importa…
FIction: 4D Future Interaction Prediction from Video
Kumar Ashutosh, Georgios Pavlakos, Kristen Grauman
Anticipating how a person will interact with objects in an environment is essential for activity understanding, but existing methods are limited to the 2D space of video frames-cap…
Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos
Sagnik Majumder, Tushar Nagarajan, Ziad Al-Halah +2
Given a multi-view video, which viewpoint is most informative for a human observer? Existing methods rely on heuristics or expensive "best-view" supervision to answer this question…