# Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition

arXiv: https://arxiv.org/abs/2605.23288 · HTML: https://mlsanity.com/paper/2605.23288/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 42 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [A Short Note about Kinetics-600](https://mlsanity.com/paper/1808.01340/) (2018)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [ActionCLIP: A New Paradigm for Video Action Recognition](https://mlsanity.com/paper/2109.08472/) (2021)
- [Prompting Visual-Language Models for Efficient Video Understanding](https://mlsanity.com/paper/2112.04478/) (2021)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2303.11797/) (2023)
- [ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning](https://mlsanity.com/paper/2206.13559/) (2022)
- [Fine-tuned CLIP Models are Efficient Video Learners](https://mlsanity.com/paper/2212.03640/) (2022)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)
- [Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2207.10866/) (2022)

## Abstract (arXiv)

Recent Open-Vocabulary Action Recognition (OVAR) methods typically aggregate visual features into a global representation before computing text alignment, a process that obscures local patch information and fine-grained spatio-temporal cues. We propose Similarity Volume Aggregation (SimVA), a framework that constructs a dense 4D spatio-temporal similarity volume from patch-level visual-text similarities. SimVA constructs a spatio-temporal similarity volume over local video tokens and action classes, and employs class sampling to ensure similarity aggregation scalable to large vocabularies. The similarity volume is refined by spatial aggregation, which contextualizes local similarity patterns to improve intra-frame consistency. Motion-aware modulation further injects inter-frame variation cues, highlighting dynamically changing regions. Mamba-based temporal aggregation then models the evolution of class-conditioned similarity patterns across frames. By maintaining dense visual-text correspondence, SimVA effectively transfers CLIP to video action recognition, achieving competitive performance across zero-shot, few-shot, and base-to-novel benchmarks.