6 papers
HumanMoveVQA: Can Video MLLMs reason about human movement in videos?
Pulkit Gera, Faegheh Sardari, Asmar Nadeem +4
Despite the rapid advance of Multimodal Large Language Models (MLLMs) in high-level video understanding, a fundamental bottleneck remains: these models collapse complex human motio…
DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding
Tanveer Hannan, Dimitrios Mallios, Parth Pathak +5
Large Vision-Language Models (LVLMs) have demonstrated strong multimodal reasoning capabilities on long and complex documents. However, their high memory footprint makes them impra…
TEn-CATG:Text-Enriched Audio-Visual Video Parsing with Multi-Scale Category-Aware Temporal Graph
Yaru Chen, Faegheh Sardari, Peiliang Zhang +4
Audio-visual video parsing (AVVP) aims to detect event categories and their temporal boundaries in videos, typically under weak supervision. Existing methods mainly focus on (i) im…
TeMTG: Text-Enhanced Multi-Hop Temporal Graph Modeling for Audio-Visual Video Parsing
Yaru Chen, Peiliang Zhang, Fei Li +4
Audio-Visual Video Parsing (AVVP) task aims to parse the event categories and occurrence times from audio and visual modalities in a given video. Existing methods usually focus on…
Reframing Dense Action Detection (RefDense): A Paradigm Shift in Problem Solving & a Novel Optimization Strategy
Faegheh Sardari, Armin Mustafa, Philip J. B. Jackson +1
Dense action detection involves detecting multiple co-occurring actions while action classes are often ambiguous and represent overlapping concepts. We argue that handling the dual…
NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative
Asmar Nadeem, Faegheh Sardari, Robert Dawes +3
Existing video captioning benchmarks and models lack causal-temporal narrative, which is sequences of events linked through cause and effect, unfolding over time and driven by char…