SurgOnAir introduces a streaming vision-language model trained on a hierarchical surgical dataset to generate real-time, multi-level narrations with explicit transition tokens.
In: Proceedings of the 2024 conference on empirical methods in natural language processing
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Sink-Token-aware Pruning (SToP) uses a sink score to suppress attention-sink tokens during visual token pruning, improving fine-grained video understanding in Video LLMs at high pruning rates.
Motion-MLLM integrates IMU egomotion data into MLLMs using cascaded filtering and asymmetric fusion to ground visual content in physical trajectories for scale-aware 3D understanding, achieving competitive accuracy at higher speed.
VLMs fail at video emotion recognition because they collapse rare emotions into common ones and process frames as an unordered bag; summarizing skipped frames in text partially recovers temporal cues.
TCA-Captioner introduces an Observer-Checker-Corrector refinement loop and TCA-Bench to address modality detachment and temporal incoherence in audiovisual video captioning.
citing papers explorer
-
SurgOnAir: Hierarchy-Aware Real-Time Surgical Video Commentary
SurgOnAir introduces a streaming vision-language model trained on a hierarchical surgical dataset to generate real-time, multi-level narrations with explicit transition tokens.
-
Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs
Sink-Token-aware Pruning (SToP) uses a sink score to suppress attention-sink tokens during visual token pruning, improving fine-grained video understanding in Video LLMs at high pruning rates.
-
Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding
Motion-MLLM integrates IMU egomotion data into MLLMs using cascaded filtering and asymmetric fusion to ground visual content in physical trajectories for scale-aware 3D understanding, achieving competitive accuracy at higher speed.
-
Why Do Vision Language Models Struggle To Recognize Human Emotions?
VLMs fail at video emotion recognition because they collapse rare emotions into common ones and process frames as an unordered bag; summarizing skipped frames in text partially recovers temporal cues.
-
Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning
TCA-Captioner introduces an Observer-Checker-Corrector refinement loop and TCA-Bench to address modality detachment and temporal incoherence in audiovisual video captioning.