MASS reformulates SSM-based feature scanning in flow-based VFI to follow dynamic motion trajectories via learnable path integration and velocity-aware sampling, claiming SOTA on challenging large-displacement cases.
super hub Baseline reference
UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
Baseline reference. 64% of citing Pith papers use this work as a benchmark or comparison.
147
Pith papers citing it
Baseline
64% of classified citations
abstract
We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data. The database consists of realistic user uploaded videos containing camera motion and cluttered background. Additionally, we provide baseline action recognition results on this new dataset using standard bag of words approach with overall performance of 44.5%. To the best of our knowledge, UCF101 is currently the most challenging dataset of actions due to its large number of classes, large number of clips and also unconstrained nature of such clips.
hub tools
citation-role summary
dataset 13
background 7
baseline 2
citation-polarity summary
claims ledger
- abstract We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data. The database consists of realistic user uploaded videos containing camera motion and cluttered background. Additionally, we provide baseline action recognition results on this new dataset using standard bag of words approach with overall performance of 44.5%. To the best of our knowledge, UCF101 is currently the most challenging dataset of actions due to its large number of classes, large number of clips and also unconstrained nature of such
authors
co-cited works
representative citing papers
T-VSS is a lightweight test-time defense that steers attacked visual features in VLMs using sample-specific low-rank subspaces and reliability-weighted entropy minimization to improve robustness.
Framework certifies VLM robustness under semantic transformations via text prompt proxies, enabling quantitative certification of safe extent intervals without per-variation data.
MMA-82 is a multi-domain benchmark with 82 micro-action categories, 77,856 instances from 454 subjects, and protocols for recognition and multi-label detection tasks including cross-domain and few-shot settings.
FS-DVS inserts a learnable spatial filter before DVS event triggering; the filter converges to center-surround kernels that emphasize mid-spatial frequencies and improve downstream detection and recognition.
VidMsg is a new benchmark dataset and QA/retrieval tasks for implicit message inference in short videos, where current models perform poorly.
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
Moment-Video benchmark shows top video MLLM achieves only 39.6% accuracy on momentary visual event tasks, with most open-source models below 25%.
VideoABC estimates video-LLM failure probability via low-dimensional attribute projection, dual quantization (k-means plus lattice), and psychophysics-inspired synthetic data.
Introduces the USV dataset of 224K short user-generated videos and benchmarks topic recognition plus video-text retrieval with MMF-Net and VTCL baselines.
PERL augments frozen CLIP with a shared recurrent reasoning module of roughly 6K parameters that iteratively refines representations via latent token injection, delivering strong base-to-novel and transfer performance across 15 benchmarks.
NeRP corrects asymmetric class confusion in VLMs for unseen classes by combining neutral-prompt priors with sample likelihood to flip predictions on confusable pairs, improving new-class accuracy while preserving base-class performance.
TeDiO regularizes temporal diagonals in diffusion transformer attention maps to produce smoother video motion while keeping per-frame quality intact.
SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
STAR improves 1-shot action recognition by up to 8.1% on SSv2-Full through semantic-temporal alignment and Mamba-based prototype refinement.
CoDAAR aligns modality-specific codebooks at the index level using Discrete Temporal Alignment and Cascading Semantic Alignment to achieve cross-modal generalization while preserving unique structures, reporting state-of-the-art results on event classification, localization, video segmentation, and跨
RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
VEBENCH is the first benchmark with 3.9K videos and 3,080 human-verified QA pairs that measures LMMs on video editing technique recognition and operation simulation, revealing a large gap to human performance.
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
E2E-WAVE achieves +5 dB PSNR and real-time 16 FPS 128x128 video over 2.3 kbps underwater channels by learning waveforms that favor semantic similarity on decoding errors.
ICNNM reformulates CNNM using pre-learned shared convolution eigenvectors to bypass SVD computations, significantly reducing time while improving recovery performance for tensor completion with arbitrary sampling.
Pairwise scoring signals in Vision Transformer token reduction are inherently unstable due to high perturbation counts and degrade in deep layers, causing collapse, while unary signals with triage enable CATIS to retain 96.9% accuracy at 63% FLOPs reduction on ViT-Large ImageNet-1K.
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
A cross-attention SAE with sparsemax attention achieves lower reconstruction loss and higher-quality concepts than fixed-sparsity baselines by making activation counts data-dependent.
citing papers explorer
-
MASS: Motion-Aligned Selective Scan for Refinement in Flow-Based Video Frame Interpolation
MASS reformulates SSM-based feature scanning in flow-based VFI to follow dynamic motion trajectories via learnable path integration and velocity-aware sampling, claiming SOTA on challenging large-displacement cases.
-
T-VSS: Test-Time Visual Subspace Steering for Adversarial Robustness of Vision-Language Models
T-VSS is a lightweight test-time defense that steers attacked visual features in VLMs using sample-specific low-rank subspaces and reliability-weighted entropy minimization to improve robustness.
-
Semantic Robustness Certification for Vision-Language Models
Framework certifies VLM robustness under semantic transformations via text prompt proxies, enabling quantitative certification of safe extent intervals without per-variation data.
-
A New Multi-Domain Benchmark for Micro-Action Recognition and Detection
MMA-82 is a multi-domain benchmark with 82 micro-action categories, 77,856 instances from 454 subjects, and protocols for recognition and multi-label detection tasks including cross-domain and few-shot settings.
-
FS-DVS: A Frequency-Selective Dynamic Visual Sensing Paradigm for Enhancing Information Completeness
FS-DVS inserts a learnable spatial filter before DVS event triggering; the filter converges to center-surround kernels that emphasize mid-spatial frequencies and improve downstream detection and recognition.
-
VidMsg: A Benchmark for Implicit Message Inference in Short Videos
VidMsg is a new benchmark dataset and QA/retrieval tasks for implicit message inference in short videos, where current models perform poorly.
-
Diffusing in the Right Space: A Systematic Study of Latent Diffusability
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
-
Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
Moment-Video benchmark shows top video MLLM achieves only 39.6% accuracy on momentary visual event tasks, with most open-source models below 25%.
-
An Attribute-Based Measure of Video Complexity
VideoABC estimates video-LLM failure probability via low-dimensional attribute projection, dual quantization (k-means plus lattice), and psychophysics-inspired synthetic data.
-
USV: Towards Understanding the User-generated Short-form Videos
Introduces the USV dataset of 224K short user-generated videos and benchmarks topic recognition plus video-text retrieval with MMF-Net and VTCL baselines.
-
PERL: Parameter Efficient Reasoning in CLIP Latent Space
PERL augments frozen CLIP with a shared recurrent reasoning module of roughly 6K parameters that iteratively refines representations via latent token injection, delivering strong base-to-novel and transfer performance across 15 benchmarks.
-
Neutral-Reference Prompting for Vision-Language Models
NeRP corrects asymmetric class confusion in VLMs for unseen classes by combining neutral-prompt priors with sample likelihood to flip predictions on confusable pairs, improving new-class accuracy while preserving base-class performance.
-
TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion
TeDiO regularizes temporal diagonals in diffusion transformer attention maps to produce smoother video motion while keeping per-frame quality intact.
-
Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
-
STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR improves 1-shot action recognition by up to 8.1% on SSv2-Full through semantic-temporal alignment and Mamba-based prototype refinement.
-
Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations
CoDAAR aligns modality-specific codebooks at the index level using Discrete Temporal Alignment and Cascading Semantic Alignment to achieve cross-modal generalization while preserving unique structures, reporting state-of-the-art results on event classification, localization, video segmentation, and跨
-
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
-
VEBench:Benchmarking Large Multimodal Models for Real-World Video Editing
VEBENCH is the first benchmark with 3.9K videos and 3,080 human-verified QA pairs that measures LMMs on video editing technique recognition and operation simulation, revealing a large gap to human performance.
-
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
-
E2E-WAVE: End-to-End Learned Waveform Generation for Underwater Video Multicasting
E2E-WAVE achieves +5 dB PSNR and real-time 16 FPS 128x128 video over 2.3 kbps underwater channels by learning waveforms that favor semantic similarity on decoding errors.
-
Inductive Convolution Nuclear Norm Minimization for Tensor Completion with Arbitrary Sampling
ICNNM reformulates CNNM using pre-learned shared convolution eigenvectors to bypass SVD computations, significantly reducing time while improving recovery performance for tensor completion with arbitrary sampling.
-
Why Training-Free Token Reduction Collapses: The Inherent Instability of Pairwise Scoring Signals
Pairwise scoring signals in Vision Transformer token reduction are inherently unstable due to high perturbation counts and degrade in deep layers, causing collapse, while unary signals with triage enable CATIS to retain 96.9% accuracy at 63% FLOPs reduction on ViT-Large ImageNet-1K.
-
Efficient Video Diffusion Models: Advancements and Challenges
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
-
Improving Sparse Autoencoder with Dynamic Attention
A cross-attention SAE with sparsemax attention achieves lower reconstruction loss and higher-quality concepts than fixed-sparsity baselines by making activation counts data-dependent.
-
Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation
LMFT enables state-of-the-art performance in video unsupervised domain adaptation by focusing on motion-rich tokens and reducing computational overhead.
-
CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion
CLIP-Inspector reconstructs OOD triggers to detect backdoors in prompt-tuned CLIP models with 94% accuracy and higher AUROC than baselines, plus a repair step via fine-tuning.
-
InstrAct: Towards Action-Centric Understanding in Instructional Videos
InstrAction pretrains video foundation models using action-centric data filtering, hard negatives, an Action Perceiver module, DTW-Align, and Masked Action Modeling to reduce static bias and outperform prior models on a new InstrAct Bench for semantic, procedural, and retrieval tasks.
-
Learning from Synthetic Data via Provenance-Based Input Gradient Guidance
A framework that applies provenance-based guidance to input gradients during synthetic data training to promote learning from target regions only.
-
FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
FrameDiT proposes Matrix Attention for DiTs to achieve SOTA video generation with improved temporal coherence and efficiency comparable to local factorized attention.
-
Adapting MLLMs for Nuanced Video Retrieval
Text-only contrastive fine-tuning of an MLLM with hard negatives produces embeddings that handle temporal, negation, and multimodal nuances in video retrieval and achieves SOTA performance.
-
SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning
SIV-Bench is a new video benchmark with 2,792 clips and 5,455 QA pairs that evaluates MLLMs on social scene understanding, state reasoning, and dynamics prediction using social relation theory.
-
Zero-shot Concept Bottleneck Models
Z-CBMs achieve zero-shot interpretable predictions by retrieving concepts from a million-vocabulary web bank via cross-modal search and regressing labels with sparse linear regression.
-
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
OpenVid-1M supplies 1 million high-quality text-video pairs and introduces MVDiT to improve text-to-video generation by better using both visual structure and text semantics.
-
NetTailor: Tuning the Architecture, Not Just the Weights
NetTailor adapts CNN architecture for new tasks by assembling pre-trained universal blocks with task-specific layers, trained via activation mimicry and complexity penalties to match accuracy while reducing size for simpler tasks.
-
The Kinetics Human Action Video Dataset
Kinetics is a new video dataset of 400 human actions with over 160000 ten-second clips collected from YouTube, accompanied by baseline action-classification results from neural networks.
-
AdaBoosting Text Prompts for Vision-Language Models
TPB is an AdaBoost-style ensemble method for text prompts in VLMs that improves few-shot accuracy by targeting hard examples and maintains gains across model transfers.
-
Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners
DeCoDe decomposes few-shot classification into binary pairwise image comparisons whose affirmative logits serve as similarity scores, enabling strong performance from unmodified MLLMs on twelve datasets.
-
Forget, Anticipate and Adapt: Test Time Training for Long Videos
FFN performs TTT on multi-hour videos by restricting updates to three frames and using a surprise metric for adaptive window sizing, plus a new EpicTours dataset.
-
Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition
A modality-aware post-hoc detector for multi-modal OOD detection in action recognition combines uni-modal prediction relationships with feature-space scores and outperforms prior methods on the MultiOOD benchmark.
-
Black-Box Continual Learning for Vision-Language Models
Introduces Black-CL black-box benchmark and BETA textual-prototype method that matches or exceeds white-box continual learning performance on ten datasets using 0.05M parameters.
-
Gold Points Sniper: Self-guided Visual Reasoning in VLM for Fine-grained Action Understanding
GPS framework adds self-guided reasoning modules to lightweight VLMs for fine-grained action understanding, claiming performance near GPT-4o with better factual accuracy on a custom CAP-based dataset.
-
TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living
TimeProVe proposes a propose-then-verify framework using lightweight action-based candidate evidence generation followed by targeted VLM verification for efficient long video temporal reasoning, achieving 7.3% improvement on OTB with 75% fewer VLM calls.
-
TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization
TivTok factorizes video clips into reusable time-invariant tokens and frame-specific time-variant tokens via Scope-Induced Factorization and Invariant Broadcasting, achieving 2.91x better compression for 128-frame videos on benchmarks.
-
RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
RepWAM introduces representation visual-action tokenizers to pretrain world action models that jointly model future visual states and latent actions under instructions for improved robot manipulation.
-
Semantically-Aware Diver Activity Recognition Framework for Effective Underwater Multi-Human-Robot Collaboration
DAR-Net applies transformer temporal reasoning with pixel-level semantic supervision to classify six diver activities on a new 2,600-image UDA dataset, reporting better accuracy than prior models in controlled tests.
-
Information-Theoretic Decomposition for Multimodal Interaction Learning
DMIL is a multimodal learning framework that decomposes sample-specific interactions into redundant, unique, and synergistic components via variational architecture and uses them for adaptive fine-tuning.
-
Hybrid Robustness Verification for Spatio-Temporal Neural Networks
STBP computes exact closed-form bounds for the first convolutional layer of spatio-temporal networks and propagates scalable approximations through the rest to certify robustness under subset-frame or patch perturbations.
-
Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting
A parameter-free approach drops redundant video tokens via temporal L1 differences in frozen latent space and reconstructs them with LIT, yielding 31x speedup over ElasticTok-CV on TokenBench and DAVIS.
-
Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation Models
GPUA learns an orthogonal mapping from VFM to VLM feature space to preserve geometry and improve cross-model compatibility for zero-shot recognition and segmentation.
-
Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals
A pre-fusion calibration module modulates multimodal features using cross-modality support and conflict cues to improve performance on five benchmarks including sentiment analysis and audio-visual tasks.