REVIEW 29 cited by
A Short Note on the Kinetics-700 Human Action Dataset
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
A Short Note on the Kinetics-700 Human Action Dataset
read the original abstract
We describe an extension of the DeepMind Kinetics human action dataset from 600 classes to 700 classes, where for each class there are at least 600 video clips from different YouTube videos. This paper details the changes introduced for this new release of the dataset, and includes a comprehensive set of statistics as well as baseline results using the I3D neural network architecture.
Forward citations
Cited by 29 Pith papers
-
SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence
SVI-Bench provides 35K hours of sports video with 9 tasks across four cognitive levels, revealing models drop from ~74% on action QA to 5% on agentic evidence integration.
-
The TIME Machine: On The Power of Motion for Efficient Perception
TIME, a masked autoencoder on synthetic point tracks, matches or exceeds large video models on temporal benchmarks with four orders of magnitude less training data and complements appearance features.
-
HumanScore: Benchmarking Human Motions in Generated Videos
HumanScore defines six metrics for kinematic plausibility, temporal stability, and biomechanical consistency to benchmark human motions in videos from thirteen state-of-the-art generation models, revealing gaps betwee...
-
Recurrent Video Masked Autoencoders
RVM uses recurrent computation inside a masked autoencoder to learn video representations that match or exceed prior video and image models on classification, tracking, and dense spatial tasks with up to 30x better pa...
-
Probing Identity-Specific Motion Signatures: A Controlled Diagnostic Study
Identity-specific free-throw motion signatures exist and are learnable by video models, but models prefer static appearance shortcuts unless silhouettes or skeletons suppress them.
-
Self-Supervised Learning of Structured Dynamics from Videos
A two-token 'primary/residual' future-feature predictor separates camera from object motion, outpacing frozen-feature baselines and matching larger supervised models on several probes.
-
SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence
SVI-Bench is a 35K-hour sports video benchmark with 9 tasks across four cognitive pillars that reveals multimodal models drop from ~73% on action QA to 5% on agentic evidence-gathering tasks.
-
The TIME Machine: On The Power of Motion for Efficient Perception
TIME is a motion-based embedding from point tracks, trained only on synthetic data via masked autoencoding, that matches state-of-the-art video model performance with up to 10,000x less training data.
-
The TIME Machine: On The Power of Motion for Efficient Perception
A motion-only embedding trained on synthetic point tracks matches or beats large appearance-based video models on temporal tasks and improves them when combined.
-
Cambrian-P: Pose-Grounded Video Understanding
Cambrian-P adds per-frame camera pose tokens and a regression head to video MLLMs, delivering 4.5-6.5% gains on spatial benchmarks, generalization to other video QA tasks, and SOTA streaming pose estimation on ScanNet.
-
Cambrian-P: Pose-Grounded Video Understanding
Adding per-frame camera-pose supervision to a video MLLM improves spatial and general video question answering by 2–6% and yields SOTA streaming pose estimates on ScanNet.
-
From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data
Video-to-robot control methods cluster into three interface families, and the field’s main bottleneck is grounding video-derived predictions into dependable closed-loop robot behavior.
-
Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos
A learned human-action manifold, combining 3D pose, 2D keypoints, appearance, and motion derivatives, scores generated videos by distance to real-action centroids and embedding smoothness, beating prior metrics on hum...
-
A Comprehensive Survey on World Models for Embodied AI
A unified three-axis taxonomy — functionality, temporal modeling, spatial representation — organizes the world-model literature for embodied AI.
-
No More Sibling Rivalry: Debiasing Human-Object Interaction Detection
A detection transformer for human-object interactions gains 9.18 mAP on HICO-DET by adding contrastive-then-calibration and merge-then-split training objectives against a diagnosed 'toxic siblings' interference bias.
-
Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders
Category-level retrieval improves when text queries are converted into multiple generated images, aggregated with a learned attention module, and fused with CLIP text similarity.
-
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
V-JEPA 2 pre-trained on massive unlabeled video achieves strong results on motion understanding and action anticipation, SOTA video QA at 8B scale, and enables zero-shot robotic planning on Franka arms using only 62 h...
-
GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
GR-2 pre-trains on web-scale videos then fine-tunes on robot data to reach 97.7% average success across over 100 manipulation tasks with strong generalization to new scenes and objects.
-
EVA-CLIP: Improved Training Techniques for CLIP at Scale
EVA-CLIP delivers improved CLIP training recipes that yield 82.0% zero-shot ImageNet-1K accuracy for a 5B-parameter model after only 9 billion samples.
-
CoCa: Contrastive Captioners are Image-Text Foundation Models
CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks.
-
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.
-
Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic
Merging task vectors extracted from fine-tuned OVAR models yields superior zero-shot generalization in out-of-distribution settings compared to the pre-trained base model.
-
From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data
A survey introduces an interface-centric taxonomy for video-to-control methods in robotic manipulation and identifies the robotics integration layer as the central open challenge.
-
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
VLM2Vec-V2 is a multimodal embedding model trained on an extended MMEB-V2 benchmark that adds video and visual document tasks and reports gains on both new and prior image benchmarks.
-
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
InternVL scales a vision model to 6B parameters and aligns it with LLMs using web data to achieve state-of-the-art results on 32 visual-linguistic benchmarks.
-
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
InternVideo combines masked video modeling and video-language contrastive learning into a single foundation model that reaches state-of-the-art results on 39 video datasets including 91.1% top-1 on Kinetics-400.
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
-
From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data
The paper surveys four classes of techniques that derive action-related supervision from human videos for VLA robot models and identifies three open challenges in episode structuring, embodiment grounding, and evaluation.
-
A Survey on Deep Learning Techniques for Action Anticipation
A literature survey reviewing deep learning approaches to action anticipation in everyday scenarios, with method classifications, dataset and metric summaries, and future directions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.