# Kronecker Mask and Interpretive Prompts are Language-Action Video Learners

arXiv: https://arxiv.org/abs/2502.03549 · HTML: https://mlsanity.com/paper/2502.03549/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2025.

## Built on by (most cited first, 4 of 4)

- [DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing](https://mlsanity.com/paper/2503.00429/) (2025)
- [Language-driven Description Generation and Common Sense Reasoning for Video Action Recognition](https://mlsanity.com/paper/2506.16701/) (2025)
- [Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition](https://mlsanity.com/paper/2604.17062/) (2026)
- [EV-CLIP: Efficient Visual Prompt Adaptation for CLIP in Few-shot Action Recognition under Visual Challenges](https://mlsanity.com/paper/2604.22595/) (2026)

## Abstract (arXiv)

Contrastive language-image pretraining (CLIP) has significantly advanced image-based vision learning. A pressing topic subsequently arises: how can we effectively adapt CLIP to the video domain? Recent studies have focused on adjusting either the textual or visual branch of CLIP for action recognition. However, we argue that adaptations of both branches are crucial. In this paper, we propose CLAVER: a Contrastive Language-Action Video Learner, designed to shift CLIP's focus from the alignment of static visual objects and concrete nouns to the alignment of dynamic action behaviors and abstract verbs. Specifically, we introduce a novel Kronecker mask attention for temporal modeling. Our tailored Kronecker mask offers three benefits 1) it expands the temporal receptive field for each token, 2) it serves as an effective spatiotemporal heterogeneity inductive bias, mitigating the issue of spatiotemporal homogenization, and 3) it can be seamlessly plugged into transformer-based models. Regarding the textual branch, we leverage large language models to generate diverse, sentence-level and semantically rich interpretive prompts of actions, which shift the model's focus towards the verb comprehension. Extensive experiments on various benchmarks and learning scenarios demonstrate the superiority and generality of our approach.