SpikeTAD proposes the first SNN-based end-to-end TAD model, reporting 67.2% mAP on THUMOS14 and 37.42% on ActivityNet-1.3 with extremely low power consumption.
Quo vadis, action recognition? a new model and the kinetics dataset
10 Pith papers cite this work, alongside 432 external citations. Polarity classification is still indexing.
10
Pith papers citing it
432
external citations · OpenAlex
citation-role summary
background 3
dataset 1
citation-polarity summary
representative citing papers
iTryOn is a diffusion-based framework that adds spatial 3D hand guidance and semantic action-aware embeddings to handle complex garment deformations during human-clothing interactions in videos.
A new large-scale triplet dataset and diffusion transformer model using coarse human masks deliver improved video virtual try-on quality and generalization in challenging real-world conditions.
M2R2 proposes a multimodal robotic representation for temporal action segmentation that combines proprioceptive and exteroceptive sensors with a novel training strategy enabling feature reuse across models, achieving new state-of-the-art results on three robotic datasets.
OrganicHAR discovers 4-8 activity categories per user from sensor signals, achieves 79% accuracy on coarse activities with ambient sensors alone and cuts VLM queries by 90% by triggering video analysis only at detected pattern moments.
Trajectory-aware local temporal modeling before spatial aggregation plus CTC viseme supervision and EMA consistency lifts DVS-Lip word accuracy to 77.49%.
Introduces LUMINA-26 low-light action dataset and Illumi-Net model achieving 75.95% Top-1 accuracy on it while surpassing prior SOTA on ELLAR.
CEZSAR uses contrastive learning to align video and sentence embeddings with automatic negative sampling, claiming state-of-the-art zero-shot action recognition on UCF-101 and Kinetics-400.
A new joint spatio-temporal enlargement model for micro-video popularity prediction using frame scoring for long sequences and a topology-aware memory bank for unbounded historical associations.
DualStreamHybrid assigns ViT-Tiny to RGB and MobileNetV2 to 20-channel flow, projects features to common space, and finds cross-attention best on UCF11 (98.12%) while weighted fusion is most consistent on UCF50 (96.86%).
citing papers explorer
-
SpikeTAD: Spiking Neural Networks for End-to-End Temporal Action Detection
SpikeTAD proposes the first SNN-based end-to-end TAD model, reporting 67.2% mAP on THUMOS14 and 37.42% on ActivityNet-1.3 with extremely low power consumption.
-
iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance
iTryOn is a diffusion-based framework that adds spatial 3D hand guidance and semantic action-aware embeddings to handle complex garment deformations during human-clothing interactions in videos.
-
TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
A new large-scale triplet dataset and diffusion transformer model using coarse human masks deliver improved video virtual try-on quality and generalization in challenging real-world conditions.
-
M2R2: MultiModal Robotic Representation for Temporal Action Segmentation
M2R2 proposes a multimodal robotic representation for temporal action segmentation that combines proprioceptive and exteroceptive sensors with a novel training strategy enabling feature reuse across models, achieving new state-of-the-art results on three robotic datasets.
-
OrganicHAR: Towards Activity Discovery in Organic Settings for Privacy Preserving Sensors Using Efficient Video Analysis
OrganicHAR discovers 4-8 activity categories per user from sensor signals, achieves 79% accuracy on coarse activities with ambient sensors alone and cuts VLM queries by 90% by triggering video analysis only at detected pattern moments.
-
TVTA: Trajectory-Aware Viseme-Guided Temporal Aggregation for Event-Based Lip Reading
Trajectory-aware local temporal modeling before spatial aggregation plus CTC viseme supervision and EMA consistency lifts DVS-Lip word accuracy to 77.49%.
-
LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actions
Introduces LUMINA-26 low-light action dataset and Illumi-Net model achieving 75.95% Top-1 accuracy on it while surpassing prior SOTA on ELLAR.
-
CEZSAR: A Contrastive Embedding Method for Zero-Shot Action Recognition
CEZSAR uses contrastive learning to align video and sentence embeddings with automatic negative sampling, claiming state-of-the-art zero-shot action recognition on UCF-101 and Kinetics-400.
-
Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction
A new joint spatio-temporal enlargement model for micro-video popularity prediction using frame scoring for long sequences and a topology-aware memory bank for unbounded historical associations.
-
A Heterogeneous Two-Stream Framework for Video Action Recognition with Comparative Fusion Analysis
DualStreamHybrid assigns ViT-Tiny to RGB and MobileNetV2 to 20-channel flow, projects features to common space, and finds cross-attention best on UCF11 (98.12%) while weighted fusion is most consistent on UCF50 (96.86%).