On the public citation graph

Efficient Video Transformers via Spatial-temporal Token Merging for Action Recognition

0 signed · 65 inferred · view as graph

Inferred edges come from two machine sources: sweeps of open repository metadata (mostly SSRN and Zenodo), and a bulk OpenAlex citation snapshot. Every row below is labelled with the one it came from. Neither is a complete citation index — absence here is not evidence of absence.

Is this your work? Sign in with ORCID and put your name on the claims that are yours.
Claim with ORCID
Reference health. See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.
See reference health

What this work says

Outgoing claims: the papers this work cites, builds on, or argues with.

inferredcites →https://doi.org/10.1007/978-3-030-58452-8_13openalex-snapshot
End-to-End Object Detection with Transformers
inferredcites →https://doi.org/10.1109/cvpr.2018.00631openalex-snapshot
Compressed Video Action Recognition
inferredcites →https://doi.org/10.1109/cvpr.2018.00675openalex-snapshot
A Closer Look at Spatiotemporal Convolutions for Action Recognition
inferredcites →https://doi.org/10.1109/cvpr.2018.00813openalex-snapshot
Non-local Neural Networks
inferredcites →https://doi.org/10.1109/cvpr.2019.00137openalex-snapshot
AdaFrame: Adaptive Frame Selection for Fast Video Recognition
inferredcites →https://doi.org/10.1109/cvpr42600.2020.00023openalex-snapshot
A Multigrid Method for Efficiently Training Video Models
inferredcites →https://doi.org/10.1109/cvpr42600.2020.00028openalex-snapshot
X3D: Expanding Architectures for Efficient Video Recognition
inferredcites →https://doi.org/10.1109/cvpr42600.2020.00099openalex-snapshot
TEA: Temporal Excitation and Aggregation for Action Recognition
inferredcites →https://doi.org/10.1109/cvpr46437.2021.00681openalex-snapshot
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
inferredcites →https://doi.org/10.1109/cvpr46437.2021.01576openalex-snapshot
MoViNets: Mobile Video Networks for Efficient Video Recognition
inferredcites →https://doi.org/10.1109/cvpr52688.2022.00320openalex-snapshot
Video Swin Transformer
inferredcites →https://doi.org/10.1109/cvpr52688.2022.01553openalex-snapshot
Masked Autoencoders Are Scalable Vision Learners
inferredcites →https://doi.org/10.1109/iccv.2017.622openalex-snapshot
The “Something Something” Video Database for Learning and Evaluating Visual Common Sense
inferredcites →https://doi.org/10.1109/iccv.2019.00209openalex-snapshot
STM: SpatioTemporal and Motion Encoding for Action Recognition
inferredcites →https://doi.org/10.1109/iccv.2019.00630openalex-snapshot
SlowFast Networks for Video Recognition
inferredcites →https://doi.org/10.1109/iccv.2019.00633openalex-snapshot
SCSampler: Sampling Salient Clips From Video for Efficient Action Recognition
inferredcites →https://doi.org/10.1109/iccv.2019.00718openalex-snapshot
TSM: Temporal Shift Module for Efficient Video Understanding
inferredcites →https://doi.org/10.1109/iccv48922.2021.00061openalex-snapshot
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
inferredcites →https://doi.org/10.1109/iccv48922.2021.00676openalex-snapshot
ViViT: A Video Vision Transformer
inferredcites →https://doi.org/10.1109/iccv48922.2021.01204openalex-snapshot
LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference
inferredcites →https://doi.org/10.1109/iccv48922.2021.01332openalex-snapshot
VidTr: Video Transformer Without Convolutions
inferredcites →https://doi.org/10.1109/tip.2023.3293763openalex-snapshot
Efficient Vision Transformer via Token Merger
inferredcites →https://doi.org/10.1109/tnnls.2023.3247103openalex-snapshot
Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semisupervised Skeleton-Based Action Recognition
inferredcites →https://doi.org/10.1109/tpami.2019.2928540openalex-snapshot
Coherence Constrained Graph LSTM for Group Activity Recognition
inferredcites →https://doi.org/10.1109/tpami.2019.2942030openalex-snapshot
Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition
inferredcites →https://doi.org/10.1109/tpami.2021.3050918openalex-snapshot
Spatiotemporal Co-Attention Recurrent Neural Networks for Human-Skeleton Motion Prediction
inferredcites →https://doi.org/10.1145/3485472openalex-snapshot
From Coarse to Fine: Hierarchical Structure-aware Video Summarization
inferredcites →https://doi.org/10.1145/3538749openalex-snapshot
Exploiting Attention-Consistency Loss For Spatial-Temporal Stream Action Recognition
inferredcites →https://doi.org/10.1145/3569584openalex-snapshot
A Differentiable Parallel Sampler for Efficient Video Classification
inferredcites →https://doi.org/10.1145/3571735openalex-snapshot
Deep Unsupervised Key Frame Extraction for Efficient Video Classification
inferredcites →https://doi.org/10.1145/3572776openalex-snapshot
HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition
inferredcites →https://doi.org/10.1145/3576857openalex-snapshot
A Novel Lightweight Audio-visual Saliency Model for Videos
inferredcites →https://doi.org/10.1145/3579359openalex-snapshot
Bidirectional Transformer GAN for Long-term Human Motion Prediction
inferredcites →https://doi.org/10.1145/3596496openalex-snapshot
Complementary Coarse-to-Fine Matching for Video Object Segmentation
inferredcites →https://doi.org/10.1609/aaai.v35i2.16235openalex-snapshot
SMART Frame Selection for Action Recognition
inferredcites →https://doi.org/10.4230/lipics.cosit.2022.18openalex-snapshot
AI-Assisted Pipeline for Dynamic Generation of Trustworthy Health Supplement Content at Scale
inferredcites →https://doi.org/10.48550/arxiv.2010.04159openalex-snapshot
Deformable DETR: Deformable Transformers for End-to-End Object Detection
inferredcites →https://doi.org/10.48550/arxiv.2010.11929openalex-snapshot
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
inferredcites →https://doi.org/10.48550/arxiv.2106.02034openalex-snapshot
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
inferredcites →https://doi.org/10.48550/arxiv.2106.05392openalex-snapshot
Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
inferredcites →https://doi.org/10.48550/arxiv.2202.07800openalex-snapshot
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations
inferredcites →https://doi.org/10.48550/arxiv.2210.04889openalex-snapshot
Turbo Training with Token Dropout
inferredcites →https://doi.org/10.48550/arxiv.2210.09461openalex-snapshot
Token Merging: Your ViT But Faster
inferredcites →https://doi.org/10.48550/arxiv.2212.06795openalex-snapshot
GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
inferredcites →https://doi.org/10.48550/arxiv.2302.02327openalex-snapshot
Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition

What points at this work

Incoming claims: where this work appears in other papers’ reference lists and arguments.

inferred← citeshttps://doi.org/10.1002/spy2.70245openalex-snapshot
Privacy‐Preserving Federated Audio‐Visual Saliency Analysis and Data Sharing Architecture for Rehabilitation of People With Disabilities
inferred← citeshttps://doi.org/10.1007/s00521-026-12358-8openalex-snapshot
Efficient compressed video action recognition via frame selection and token merging in vision transformers
inferred← citeshttps://doi.org/10.1007/s10586-025-05478-8openalex-snapshot
Midframe-centric token merging for efficient video transformer
inferred← citeshttps://doi.org/10.1007/s11227-025-06927-2openalex-snapshot
An efficient video transformer network with token discard and keyframe enhancement for action recognition
inferred← citeshttps://doi.org/10.1016/j.atech.2026.102263openalex-snapshot
SAM-Net: A hybrid Self-attention–Mamba network for similar abnormal behavior recognition in rainbow trout
inferred← citeshttps://doi.org/10.1016/j.cosrev.2026.101003openalex-snapshot
Video vision transformer: to discover the "four secrets" of video patches
inferred← citeshttps://doi.org/10.1016/j.engappai.2025.113300openalex-snapshot
Automatic stem phenotyping in soybean using keypoint detection
inferred← citeshttps://doi.org/10.1016/j.neunet.2025.108313openalex-snapshot
RepAttn3D: Re-parameterizing 3D attention with spatiotemporal augmentation for video understanding
inferred← citeshttps://doi.org/10.1016/j.patcog.2026.113971openalex-snapshot
VideoAligner: Text-driven feature decomposition for precise video–text alignment
inferred← citeshttps://doi.org/10.1109/iccv51701.2025.01806openalex-snapshot
Unified Visual Generation via Next-Set Prediction in Continuous Domain
inferred← citeshttps://doi.org/10.1109/micro61859.2024.00015openalex-snapshot
AdapTiV: Sign-Similarity Based Image-Adaptive Token Merging for Vision Transformer Acceleration
inferred← citeshttps://doi.org/10.1109/tgrs.2025.3631727openalex-snapshot
CFDNet: Coupling Computational Fluid Dynamics With Convolutional Neural Networks for Gas Detection Using Thermal Infrared Multispectral Video
inferred← citeshttps://doi.org/10.1109/tnnls.2025.3602089openalex-snapshot
Toward an Effective Action-Region Tracking Framework for Fine-Grained Video Action Recognition
inferred← citeshttps://doi.org/10.1145/3673657openalex-snapshot
TPTE: Text-Guided Patch Token Exploitation for Unsupervised Fine-Grained Representation Learning
inferred← citeshttps://doi.org/10.1145/3712594openalex-snapshot
Mixed Attention and Channel Shift Transformer for Efficient Action Recognition
inferred← citeshttps://doi.org/10.1145/3737461openalex-snapshot
Scaled Background Swap: Video Augmentation for Action Quality Assessment with Background Debiasing
inferred← citeshttps://doi.org/10.1145/3777469openalex-snapshot
MatPose: A 2D Human Pose Estimation Model with Hybrid Mamba-Transformer
inferred← citeshttps://doi.org/10.1145/3832322openalex-snapshot
Global-local Temporal Modeling Enhanced 2DCNN with Category-supervised Contrastive Learning for Action Recognition
inferred← citeshttps://doi.org/10.2139/ssrn.7357566openalex-snapshot
REMA-Net: Real-Time Human Action Recognition via Caption-Guided Dual-Stream Attention
inferred← citeshttps://doi.org/10.3390/agronomy15040791openalex-snapshot
SmartPod: An Automated Framework for High-Precision Soybean Pod Counting in Field Phenotyping
Editorial review for independent work. ICSAC — the Institute for Complexity Science and Advanced Computing — runs a structured editorial panel for researchers publishing outside journals, and publishes on CiteStamp rails. Submission is free and goes through ORCID: icsacinstitute.org/submit.