RobustSora benchmark demonstrates that current AI video detectors rely heavily on visible watermarks, with average accuracy drops of 6.6 percentage points when watermarks are erased and increased false alarms when watermarks are spoofed onto real videos.
hub Canonical reference
Is space-time attention all you need for video understanding?
Canonical reference. 83% of citing Pith papers cite this work as background.
14
Pith papers citing it
1,359
external citations · external index
Background
83% of classified citations
hub tools
citation-role summary
background 5
baseline 1
citation-polarity summary
representative citing papers
LookWhen factorizes video recognition into learning when, where, and what to compute via uniqueness-based token selection and dual-teacher distillation, achieving better accuracy-FLOPs trade-offs than baselines on multiple datasets.
A diffusion model for video generation extends image architectures with joint image-video training and improved conditional sampling, delivering first large-scale text-to-video results and state-of-the-art performance on video prediction and unconditional generation benchmarks.
Tensor Memory augments Transformers with a constant-size 3D voxel grid using differentiable soft writes at predicted locations, local interaction, and gated recurrent dynamics to decouple memory capacity from sequence length.
CAM-VFD detects video forgeries by using cross-attention to identify contradictions between CLIP appearance, VideoMAE motion, and MiDaS depth features.
Alignment pattern analysis reveals that models aligned to individual brain ROIs do not reproduce the stable cross-region alignment profiles observed across human subjects.
The MOSS module learns and combines multi-order space-time self-similarity features to enhance temporal dynamics modeling in videos across action recognition, VQA, and robotic tasks.
Cataract-LMM is a new multi-source dataset of 3000 annotated phacoemulsification videos enabling benchmarks for phase recognition, scene segmentation, interaction tracking, and automated skill assessment.
SkillFormer, PATS, and ProfVLM deliver state-of-the-art multi-view proficiency estimation on Ego-Exo4D with up to 20x fewer parameters by combining selective fusion, dense sampling, and generative feedback.
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.
T-SHAP stabilizes SHAP attributions temporally for LSTM fall detection, achieving 94.3% accuracy and improved faithfulness on NTU RGB+D dataset.
Time-series Vision Transformer reconstructs cloud-covered multispectral imagery by integrating temporal coherence and SAR data via attention, outperforming non-time-series and SAR-free baselines.
A CNN-plus-state-space-model multi-task network predicts laser weld penetration state (99.35% accuracy), depth (1.79 mm error), and cross-section morphology (95.65% accuracy) from top-view weld-pool images and welding parameters.
Signed Dual Attention is a parameter-free attention module that models signed dependencies in time series via dual message passing to achieve two-head expressiveness in one block.
citing papers explorer
-
RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection
RobustSora benchmark demonstrates that current AI video detectors rely heavily on visible watermarks, with average accuracy drops of 6.6 percentage points when watermarks are erased and increased false alarms when watermarks are spoofed onto real videos.
-
LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute
LookWhen factorizes video recognition into learning when, where, and what to compute via uniqueness-based token selection and dual-teacher distillation, achieving better accuracy-FLOPs trade-offs than baselines on multiple datasets.
-
Video Diffusion Models
A diffusion model for video generation extends image architectures with joint image-video training and improved conditional sampling, delivering first large-scale text-to-video results and state-of-the-art performance on video prediction and unconditional generation benchmarks.
-
Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers
Tensor Memory augments Transformers with a constant-size 3D voxel grid using differentiable soft writes at predicted locations, local interaction, and gated recurrent dynamics to decouple memory capacity from sequence length.
-
CAM-VFD: Cross-Attention Multimodal Video Forgery Detection
CAM-VFD detects video forgeries by using cross-attention to identify contradictions between CLIP appearance, VideoMAE motion, and MiDaS depth features.
-
Only Brains Align with Brains: Cross-Region Alignment Patterns Expose Limits of Normative Models
Alignment pattern analysis reveals that models aligned to individual brain ROIs do not reproduce the stable cross-region alignment profiles observed across human subjects.
-
Exploring High-Order Self-Similarity for Video Understanding
The MOSS module learns and combines multi-order space-time self-similarity features to enhance temporal dynamics modeling in videos across action recognition, VQA, and robotic tasks.
-
Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis
Cataract-LMM is a new multi-source dataset of 3000 annotated phacoemulsification videos enabling benchmarks for phase recognition, scene segmentation, interaction tracking, and automated skill assessment.
-
Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback
SkillFormer, PATS, and ProfVLM deliver state-of-the-art multi-view proficiency estimation on Ego-Exo4D with up to 20x fewer parameters by combining selective fusion, dense sampling, and generative feedback.
-
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.
-
Explainable Fall Detection for Elderly Monitoring via Temporally Stable SHAP in Skeleton-Based Human Activity Recognition
T-SHAP stabilizes SHAP attributions temporally for LSTM fall detection, achieving 94.3% accuracy and improved faithfulness on NTU RGB+D dataset.
-
Vision Transformer-Based Time-Series Image Reconstruction for Cloud-Filling Applications
Time-series Vision Transformer reconstructs cloud-covered multispectral imagery by integrating temporal coherence and SAR data via attention, outperforming non-time-series and SAR-free baselines.
-
A multi-task spatiotemporal deep neural network for predicting penetration depth and morphology in laser welding
A CNN-plus-state-space-model multi-task network predicts laser weld penetration state (99.35% accuracy), depth (1.79 mm error), and cross-section morphology (95.65% accuracy) from top-view weld-pool images and welding parameters.
-
Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting
Signed Dual Attention is a parameter-free attention module that models signed dependencies in time series via dual message passing to achieve two-head expressiveness in one block.