collaborators

6 papers

cs.CV2026

TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living

Arkaprava Sinha, Dominick Reilly, Siddharth Krishnan +2

Long Video Question Answering (LVQA) requires identifying sparse, query-relevant evidence within hours-long untrimmed videos. Existing approaches either process videos densely with…

cs.CV2026

UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning

Wenhao Chi, Arkaprava Sinha, Dominick Reilly +2

Egocentric video understanding is inherently limited by the narrow perspective of wearable cameras: a single viewpoint, a single modality, a single model cannot capture the full ri…

cs.CV2025

MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos

Arkaprava Sinha, Monish Soundar Raj, Pu Wang +3

Temporal Action Detection (TAD) in untrimmed videos poses significant challenges, particularly for Activities of Daily Living (ADL) requiring models to (1) process long-duration vi…

cs.CV2025

DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping

Weston Bondurant, Arkaprava Sinha, Hieu Le +2

Diffusion-based approaches have recently achieved strong results in face swapping, offering improved visual quality over traditional GAN-based methods. However, even state-of-the-a…

cs.CV2025

LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living

Dominick Reilly, Rajatsubhra Chakraborty, Arkaprava Sinha +5

Current Large Language Vision Models (LLVMs) trained on web videos perform well in general video understanding but struggle with fine-grained details, complex human-object interact…

cs.CV2025

SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living

Arkaprava Sinha, Dominick Reilly, Francois Bremond +2

The introduction of vision-language models like CLIP has enabled the development of foundational video models capable of generalizing to unseen videos and human actions. However, t…