REVIEW 6 cited by
VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models, Video Large Language Models (video LLMs) can handle multiple tasks concurrently in a zero-shot manner. Consequently, exploring the application of video LLMs for VTG tasks has become a burgeoning research area. However, despite considerable advancements in video content understanding, video LLMs often struggle to accurately pinpoint timestamps within videos, limiting their effectiveness in VTG tasks. To address this, we introduce VTG-LLM, a model designed to enhance video LLMs' timestamp localization abilities. Our approach includes: (1) effectively integrating timestamp knowledge into visual tokens; (2) incorporating absolute-time tokens to manage timestamp knowledge without concept shifts; and (3) introducing a lightweight, high-performance, slot-based token compression technique designed to accommodate the demands of a large number of frames to be sampled for VTG tasks. Additionally, we present VTG-IT-120K, a collection of publicly available VTG datasets that we have re-annotated to improve upon low-quality annotations. Our comprehensive experiments demonstrate the superior performance of VTG-LLM in comparison to other video LLM methods across a variety of VTG tasks.
Forward citations
Cited by 6 Pith papers
-
Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning
Latent event planning plus event-factorized attention restructures the AR dependency graph so dense video captions can be decoded in parallel with higher accuracy and 3–4× wall-clock speedup.
-
DisTime: Distribution-based Time Representation for Video Large Language Models
A single learnable time token, decoded into a probability distribution over time bins, improves temporal grounding in Video-LLMs and is trained partly on a new 1.25M-event pseudo-labeled dataset.
-
TimePLE: Rethinking Temporal Representation for Video Temporal Grounding
TimePLE predicts a whole video interval as a joint distribution over a position-duration square, rather than predicting start and end separately, and reports higher mIoU across four VTG benchmarks.
-
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
An open 4B video MLLM with inflated-3D ViT tokenization and adaptive streaming perception outperforms comparable open models on general, long-video, and streaming benchmarks while using fewer visual tokens.
-
EgoExo-Con: Exploring View-Invariant Video Temporal Understanding
Most Video-LLMs answer temporal questions far less consistently when the same event is shown from ego and exo views, and a GRPO variant with a reasoning-similarity reward partially closes the gap.
-
Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning
A supervised fine-tuning plus difficulty-filtered reinforcement learning recipe improves video temporal grounding on three benchmarks, with datasets and models released.
Discussion (0). Continue with ORCID to comment.