arXiv Computer Vision
Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 16
Exploring the Temporal Consistency for Point-Level Weakly-Supervised Temporal Action Localization
arXiv:2602.05718v2 Announce Type: replace Abstract: Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per act...
arXiv Computer Vision
Oct 27
P2P-Former: Bridging the Supervision Gap Between Point and Proposal in Temporal Action Localization
arXiv:2610.34618v1 Announce Type: new Abstract: Recently, point-supervised temporal action localization has attracted increasing attention due to its low annotation cost (only one frame per action in...
arXiv AI
3d ago
Grounding in the Dark: Text-Only Training for Zero-Shot Video Temporal Localization
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 Computer Vision
Sep 2
ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits
arXiv:2609.00505v1 Announce Type: new Abstract: Video-text models adapted from image-text architectures (e.g., CLIP) frequently exhibit temporal blindness, the inability to perceive fundamental cues...
arXiv Computer Vision
3d ago
Beyond Scene Shortcuts: Action-Centric Video-Text Alignment for Fine-Grained Action Understanding
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 Machine Learning
Jul 2
MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
arXiv:2607. 00858v1 Announce Type: cross Abstract: Contrastive pre-training has propelled video-text alignment, yet models often inherit the critical limitations of their image-text predecessors like CLIP, resulting in entangled representations.