arXiv:2608. 20127v1 Announce Type: new Abstract: Video Temporal Grounding (VTG) faces significant challenges when natural language queries must distinguish between multiple events involving visually similar entities, particularly when relying on fine-grained visual attributes that are difficult to describe accurately in words alone.
The paper introduces Invert4TVG, a temporal video grounding framework that adds inversion tasks to preserve action understanding. It defines three inversion tasks—Verb Completion, Action Recognition, and Video Description—derived from existing TVG annotations and integrates them via reinforcement learning. Experiments demonstrate a 7.1% improvement in R1@0.7 on Charades-STA for a 3B model, outperforming state‑of‑the‑art methods.
TraCE introduces a trajectory‑aware concept framework for explainable video understanding, clustering optical‑flow trajectories to discover motion concepts that capture dynamic evidence from people, objects, and interactions. These concepts, along with static object and scene concepts, form a typed interface that supports action recognition and question‑conditioned video question answering. Across six benchmarks, TraCE achieves competitive performance with only a 1.0‑point drop in action recognition accuracy and a 0.4‑point gain in VQA, while motion perturbation and concept‑removal tests demonstrate semantic alignment and decision faithfulness.
The paper explores training a large language model solely on textual video descriptions to perform zero‑shot video temporal localization, eliminating the need for paired video‑text data during training. Using a 134K‑example corpus and adapting Qwen3‑8B with LoRA on CLIP or LLM2CLIP embeddings, the authors evaluate on Charades‑STA and QV‑Highlights, achieving modest performance when directly replacing text with frame embeddings. They introduce Nearest Entity Replacement (NER), a training‑free mapping that represents each video frame by the mean of its nearest text‑entity embeddings, which significantly improves results and narrows the modality gap.
arXiv:2611.06302v1 Announce Type: new Abstract: Fine-grained action understanding requires vision-language models to ground what an agent does, how it acts, and why it acts in spatio-temporal evidenc...
arXiv:2610.08674v1 Announce Type: new Abstract: Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independentl...
TimeBlind is a diagnostic benchmark designed to evaluate fine‑grained spatio‑temporal compositionality in video large language models (LLMs). It categorizes temporal understanding into three levels—atomic event recognition, event property characterization, and reasoning about event interdependencies—and uses a minimal‑pairs paradigm where video pairs share identical static content but differ only in temporal structure. Across 20 state‑of‑the‑art MLLMs tested on 600 curated instances, the best model achieved only 48.2% instance accuracy, far below human performance of 98.2%, highlighting a reliance on static visual shortcuts rather than true temporal reasoning.
arXiv:2605.13803v2 Announce Type: replace Abstract: Video temporal grounding (VTG) takes an untrimmed video and a natural-language query as input and localizes the temporal moment that best matches t...
The paper introduces Temporally-Grounded Language Generation (TGLG), a benchmark that tests vision‑language models on their ability to produce semantically accurate and temporally precise utterances in real‑time settings. It identifies perceptual updating and contingency awareness as key capabilities, curates datasets from sports broadcasting and egocentric interactions, and proposes the TRACE metric to jointly evaluate semantic similarity and temporal alignment. The authors also present VLM‑TSI, a model that interleaves visual and linguistic tokens in a time‑synchronized manner, achieving better performance than a strong baseline yet still showing modest overall results, underscoring the challenge of real‑time VLMs.
The paper introduces query‑guided grounding methods for video understanding, covering object‑level, relationship‑level, and moment‑level tasks. For object grounding, QDETRv and TOViT enable one‑shot and few‑shot localization of unseen objects using query‑context fusion, memory modules, and language‑aligned vision encoders. Relationship grounding is addressed with a few‑shot referring framework that optimizes a T‑partite random field, while moment grounding is tackled by the Moment Alignment Transformer (MATR), which employs dynamic time warping and self‑supervised pretraining for video‑to‑video and text‑to‑video retrieval.
arXiv:2610.19526v1 Announce Type: new Abstract: Temporal action detection in long untrimmed videos suffers from inaccurate localization and low-quality proposals, especially with sparse annotations a...
arXiv:2509.02807v2 Announce Type: replace Abstract: Multi-modal large language models (MLLMs) have shown impressive generalization across tasks using images and text modalities. While their extension...