Zero-Shot Action Recognition

Benchmarks archive 2025-07-28

7 leaderboard tables shown for this task, 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 40 papers with code (83 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
  3 Oct 2023 6 repositories listed Syntology ran 7 of 14 samples · 7 unverified
  We thus propose VIDAL-10M with Video, Infrared, Depth, Audio and their corresponding Language, naming as VIDAL-10M.
• Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
  31 Dec 2022 5 repositories listed
  In this paper, we propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We introduce the Video Attribute Association mechanism, which leverages the…
• Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
  4 Jul 2022 5 repositories listed
  In this study, we focus on transferring knowledge for video classification tasks.
• EVA-CLIP: Improved Training Techniques for CLIP at Scale
  27 Mar 2023 4 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  Our approach incorporates new techniques for representation learning, optimization, and augmentation, enabling EVA-CLIP to achieve superior performance compared to previous CLIP models with the same number of parameters…
• Learning a Deep Embedding Model for Zero-Shot Learning
  15 Nov 2016 4 repositories listed
  In this paper we argue that the key to make deep ZSL models succeed is to choose the right embedding space.
• Leveraging Temporal Contextualization for Video Action Recognition
  15 Apr 2024 2 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
  To be specific, we introduce Temporal Contextualization (TC), a layer-wise temporal information infusion mechanism for videos, which 1) extracts core information from each frame, 2) connects relevant information across…
• Expanding Language-Image Pretrained Models for General Video Recognition
  4 Aug 2022 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Extensive experiments demonstrate that our approach is effective and can be generalized to different video recognition scenarios.
• FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks
  24 Mar 2022 2 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  Large-scale pretrained image-text models have shown incredible zero-shot performance in a handful of tasks, including video ones such as action recognition and text-to-video retrieval.
• Bridging Video-text Retrieval with Multiple Choice Questions
  13 Jan 2022 2 repositories listed Syntology ran 13 of 24 samples · 11 unverified · 6 pointer-only (licence)
  As an additional benefit, our method achieves competitive results with much shorter pre-training videos on single-modality downstream tasks, e.
• ActionCLIP: A New Paradigm for Video Action Recognition
  17 Sep 2021 2 repositories listed Syntology ran 5 of 9 samples · 4 unverified
  Moreover, to handle the deficiency of label texts and make use of tremendous web data, we propose a new paradigm based on this multimodal learning framework for action recognition, which we dub "pre-train, prompt and…
• Label-Embedding for Image Classification
  30 Mar 2015 2 repositories listed
  Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce.
• Evaluation of Output Embeddings for Fine-Grained Image Classification
  30 Sep 2014 2 repositories listed
  Image classification has advanced significantly in recent years with the availability of large-scale image sets.
• Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP
  13 Dec 2024 1 repository listed
  Zero-shot action recognition (ZSAR) requires collaborative multi-modal spatiotemporal understanding.
• LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition
  27 Nov 2024 1 repository listed
  Specifically, we obtain relative gains of 3.
• TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition
  16 Nov 2024 1 repository listed
  In zero-shot skeleton-based action recognition, aligning skeleton features with the text features of action labels is essential for accurately predicting unseen actions.
• Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition
  19 Jun 2024 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  While remarkable progress has been made on supervised skeleton-based action recognition, the challenge of zero-shot recognition remains relatively unexplored.
• EZ-CLIP: Efficient Zeroshot Video Action Recognition
  13 Dec 2023 1 repository listed Syntology ran 9 of 13 samples · 4 unverified
  Recent advancements in large-scale pre-training of visual-language models on paired image-text data have demonstrated impressive generalization capabilities for zero-shot tasks.
• OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition
  30 Nov 2023 1 repository listed Syntology ran 1 of 2 samples · 1 unverified
  Due to the resource-intensive nature of training vision-language models on expansive video data, a majority of studies have centered on adapting pre-trained image-language models to the video domain.
• Telling Stories for Common Sense Zero-Shot Action Recognition
  29 Sep 2023 1 repository listed
  The textual narratives forge connections between seen and unseen classes, overcoming the bottleneck of labeled data that has long impeded advancements in this exciting domain.
• Orthogonal Temporal Interpolation for Zero-Shot Video Recognition
  14 Aug 2023 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  We propose a model called OTI for ZSVR by employing orthogonal temporal interpolation and the matching loss based on VLMs.
• Actor-agnostic Multi-label Action Recognition with Multi-modal Query
  20 Jul 2023 1 repository listed
  Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors.
• InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
  13 Jul 2023 1 repository listed
  Specifically, we utilize a multi-scale approach to generate video-related descriptions.
• Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting
  6 Apr 2023 1 repository listed Syntology ran 5 of 9 samples · 4 unverified
  Through this prompting scheme, we can achieve state-of-the-art zero-shot performance on Kinetics-600, HMDB51 and UCF101 while remaining competitive in the supervised setting.
• MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
  15 Mar 2023 1 repository listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  We adapt a VL model for zero-shot and few-shot action recognition using a collection of unlabeled videos and an unpaired action dictionary.
• Global Semantic Descriptors for Zero-Shot Action Recognition
  24 Sep 2022 1 repository listed
  This work introduces a new ZSAR method based on the relationships of actions-objects and actions-descriptive sentences.
• A CLIP-Hitchhiker's Guide to Long Video Retrieval
  17 May 2022 1 repository listed
  Our goal in this paper is the adaptation of image-text models for long video retrieval.
• MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval
  26 Apr 2022 1 repository listed
  Dominant pre-training work for video-text retrieval mainly adopt the "dual-encoder" architectures to enable efficient retrieval, where two separate encoders are used to contrast global video and text representations,…
• Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification
  29 Mar 2022 1 repository listed Syntology ran 2 of 5 samples · 3 unverified · 5 pointer-only (licence)
  Further, we synthesize features of unseen classes by proposing a class generator that interpolates and extrapolates the features of seen classes.
• Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions
  28 Mar 2022 1 repository listed
  However, due to the complexity of actions, it remains challenging to transfer knowledge learned from source to target action domains.
• End-to-End Semantic Video Transformer for Zero-Shot Action Recognition
  10 Mar 2022 1 repository listed
  While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction.

Syntology lines on 14 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.