GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models

• URL: http://arxiv.org/abs/2604.10385v1
• Date: Sun, 12 Apr 2026 00:01:51 GMT
• Title: GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models
• Abstract summary: We introduce GTASA, a corpus of multiactor videos with per-frame spatial- graphs and event-level temporal mappings.<n>We produce it based on Graphs of Events in Space and Time (EST): GEST-Engine.<n>Probing four frozen video encoders across 11temporal reasoning tasks enabled GTASA's exact 3D ground truth.
• Score: 4.964902130083661
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating complex multi-actor scenario videos remains difficult even for state-of-the-art neural generators, while evaluating them is hard due to the lack of ground truth for physical plausibility and semantic faithfulness. We introduce GTASA, a corpus of multi-actor videos with per-frame spatial relation graphs and event-level temporal mappings, and the system that produced it based on Graphs of Events in Space and Time (GEST): GEST-Engine. We compare our method with both open and closed source neural generators and prove both qualitatively (human evaluation of physical validity and semantic alignment) and quantitatively (via training video captioning models) the clear advantages of our method. Probing four frozen video encoders across 11 spatiotemporal reasoning tasks enabled by GTASA's exact 3D ground truth reveals that self-supervised encoders encode spatial structure significantly better than VLM visual encoders.

Related papers

• What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models [15.808524963857119]
  We leverage lightweight probes trained to discover three temporally grounded properties: (i) camera motion, understanding (ii) intuitive physics, and (iii) anomaly detection.<n>We find that temporal features from individual videos form smooth low-temporal trajectories in representation space, suggesting that camera motion is not only linearly decodable but also geometrically organized.
  arXiv  Detail & Related papers  (2026-09-01T17:17:04Z)
• Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding [50.098085774845195]
  We propose a paradigm shift by leveraging the implicit spatial prior within large-scale generation models.<n>We introduce GeneEGA-3D (Video Extracted Generative Awareness), a plug-and-play framework that repurposes a pre-trained video diffusion model as a Latent World Simulator.
  arXiv  Detail & Related papers  (2026-03-19T17:59:58Z)
• Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning [18.15310805625469]
  We present Know-Show, a new benchmark designed to evaluate multimodal Video-Language Models (Video-LMs)<n>Know-Show unifies reasoning and localization within a single evaluation framework consisting of five scenarios across spatial (person, object, person-object, and hand-object) and temporal dimensions.<n>Built from Charades, Action Genome, and Ego4D with 2.5K human-language questions, the benchmark exposes significant gaps between current Video-LMs and human reasoning.<n>To bridge this gap, we propose GRAM, a training-free plug-in that augments Video-LMs with fine-grained grounding
  arXiv  Detail & Related papers  (2025-12-05T08:15:49Z)
• SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding [64.86119288520419]
  multimodal language models struggle with spatial reasoning across time and space.<n>We present SIMS-V -- a systematic data-generation framework that leverages the privileged information of 3D simulators.<n>Our approach demonstrates robust generalization, maintaining performance on general video understanding while showing substantial improvements on embodied and real-world spatial tasks.
  arXiv  Detail & Related papers  (2025-11-06T18:53:31Z)
• Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence [70.2803680525165]
  We introduce Open-o3 Video, a non-agent framework that integrates explicit evidence into video reasoning.<n>The model highlights key objects and bounding boxes alongside its answers, allowing reasoning to be grounded in concrete visual observations.<n>On V-STAR benchmark, Open-o3 Video achieves state-of-the-art performance, raising mAM by 14.4% and mL timestamp by 24.2%.
  arXiv  Detail & Related papers  (2025-10-23T14:05:56Z)
• ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models [63.12671761097701]
  Vision-Language Models (Ms) struggle to analyze elements like traveled distance and speed of moving objects.<n>We construct a benchmark dataset referred to as STKit and ST-Bench.<n>We show that ST-VLM generalizes robustly across diverse domains and tasks.
  arXiv  Detail & Related papers  (2025-03-25T05:08:06Z)
• Deeply-Coupled Convolution-Transformer with Spatial-temporal Complementary Learning for Video-based Person Re-identification [91.56939957189505]
  We propose a novel spatial-temporal complementary learning framework named Deeply-Coupled Convolution-Transformer (DCCT) for high-performance video-based person Re-ID. Our framework could attain better performances than most state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-27T12:16:44Z)
• LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision [58.6039004982056]
  We propose a neuro-symbolic framework to enable training generators using only video captions.<n>An alignment algorithm overcomes the challenges of weak supervision by leveraging a differentiable symbolic reasoner.<n>We evaluate our method on three video datasets: OpenPVSG, 20BN, and MUGEN.
  arXiv  Detail & Related papers  (2023-04-15T22:24:05Z)
• Autoencoding Video Latents for Adversarial Video Generation [0.0]
  AVLAE is a two stream latent autoencoder where the video distribution is learned by adversarial training. We demonstrate that our approach learns to disentangle motion and appearance codes even without the explicit structural composition in the generator.
  arXiv  Detail & Related papers  (2022-01-18T11:42:14Z)
• Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics [74.6968179473212]
  This paper proposes a novel pretext task to address the self-supervised learning problem. We compute a series of partitioning-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion. A neural network is built and trained to yield the statistical summaries given the video frames as inputs.
  arXiv  Detail & Related papers  (2020-08-31T08:31:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.