Cover Image

FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Xiaohu, Zhou, Hao, Yao, Kun, Han, Kai
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethinking CLIP-based Video Learners in Cross-Domain Open-Vocabulary Action Recognition
by: Lin, Kun-Yu, et al.
Published: (2024)

EZ-CLIP: Efficient Zeroshot Video Action Recognition
by: Ahmad, Shahzad, et al.
Published: (2023)

Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation
by: Chi, Zhixiang, et al.
Published: (2025)

Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers
by: Li, Xianhang, et al.
Published: (2025)

Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation
by: Chi, Zhixiang, et al.
Published: (2025)

OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models
by: Ray, Lala Shakti Swarup, et al.
Published: (2024)

FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation
by: Chen, Xi, et al.
Published: (2024)

CLIP with Quality Captions: A Strong Pretraining for Vision Tasks
by: Vasu, Pavan Kumar Anasosalu, et al.
Published: (2024)

Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation
by: Zhang, Bingfeng, et al.
Published: (2024)

Advancing Vision-based Human Action Recognition: Exploring Vision-Language CLIP Model for Generalisation in Domain-Independent Tasks
by: Shandilya, Utkarsh, et al.
Published: (2025)

C3Box: A CLIP-based Class-Incremental Learning Toolbox
by: Sun, Hao, et al.
Published: (2026)

kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies
by: Gui, Zhongrui, et al.
Published: (2024)

External Knowledge Injection for CLIP-Based Class-Incremental Learning
by: Zhou, Da-Wei, et al.
Published: (2025)

Exploring Simple Open-Vocabulary Semantic Segmentation
by: Lai, Zihang
Published: (2024)

Anytime Continual Learning for Open Vocabulary Classification
by: Zhu, Zhen, et al.
Published: (2024)

Exploring Open-Vocabulary Object Recognition in Images using CLIP
by: Chen, Wei Yu, et al.
Published: (2026)

Breaking the Limits of Open-Weight CLIP: An Optimization Framework for Self-supervised Fine-tuning of CLIP
by: Mehta, Anant, et al.
Published: (2026)

Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition
by: Li, Kun, et al.
Published: (2024)

LMSeg: Unleashing the Power of Large-Scale Models for Open-Vocabulary Semantic Segmentation
by: Tang, Huadong, et al.
Published: (2024)

On the Utility of 3D Hand Poses for Action Recognition
by: Shamil, Md Salman, et al.
Published: (2024)

Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning
by: Li, Yan, et al.
Published: (2023)

COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm
by: Qian, Zekun, et al.
Published: (2026)

CLIP-driven Outliers Synthesis for few-shot OOD detection
by: Sun, Hao, et al.
Published: (2024)

OVGaussian: Generalizable 3D Gaussian Segmentation with Open Vocabularies
by: Chen, Runnan, et al.
Published: (2024)

Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning
by: Fan, Xiaomeng, et al.
Published: (2025)

AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
by: Xie, Zhen-Hao, et al.
Published: (2026)

DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection
by: Cappellino, Chiara, et al.
Published: (2025)

LADA: Scalable Label-Specific CLIP Adapter for Continual Learning
by: Luo, Mao-Lin, et al.
Published: (2025)

Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition
by: Peng, Pei, et al.
Published: (2025)

Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation
by: Bai, Sule, et al.
Published: (2024)

Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
by: Hu, Tao, et al.
Published: (2025)

Taylor Videos for Action Recognition
by: Wang, Lei, et al.
Published: (2024)

ECOR: Explainable CLIP for Object Recognition
by: Rasekh, Ali, et al.
Published: (2024)

Lightweight Modular Parameter-Efficient Tuning for Open-Vocabulary Object Detection
by: Faye, Bilal, et al.
Published: (2024)

Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs
by: Kuchibhotla, Hari Chandana, et al.
Published: (2025)

TV100: A TV Series Dataset that Pre-Trained CLIP Has Not Seen
by: Zhou, Da-Wei, et al.
Published: (2024)

DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition
by: Cheng, Haozhe, et al.
Published: (2024)

ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
by: Fan, Jiawei, et al.
Published: (2024)

Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning
by: Hümmer, Christoph, et al.
Published: (2023)

MIP: CLIP-based Image Reconstruction from PEFT Gradients
by: Zhou, Peiheng, et al.
Published: (2024)