# Seeing Fast and Slow: Learning the Flow of Time in Videos

arXiv: https://arxiv.org/abs/2604.21931 · HTML: https://mlsanity.com/paper/2604.21931/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 68 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 30 of 56)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [MotionCtrl: A Unified and Flexible Motion Controller for Video Generation](https://mlsanity.com/paper/2312.03641/) (2023)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation](https://mlsanity.com/paper/2407.02371/) (2024)
- [Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation](https://mlsanity.com/paper/1712.00080/) (2017)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Unsupervised Representation Learning by Sorting Sequences](https://mlsanity.com/paper/1708.01246/) (2017)
- [Real-Time Intermediate Flow Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2011.06294/) (2020)
- [Video Frame Synthesis using Deep Voxel Flow](https://mlsanity.com/paper/1702.02463/) (2017)
- [SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow](https://mlsanity.com/paper/2405.14793/) (2024)
- [SpeedNet: Learning the Speediness in Videos](https://mlsanity.com/paper/2004.06130/) (2020)
- [TransNet V2: An effective deep network architecture for fast shot transition detection](https://mlsanity.com/paper/2008.04838/) (2020)
- [Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning](https://mlsanity.com/paper/2503.15558/) (2025)
- [Video Frame Interpolation via Adaptive Convolution](https://mlsanity.com/paper/1703.07514/) (2017)
- [AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers](https://mlsanity.com/paper/2411.18673/) (2024)
- [FILM: Frame Interpolation for Large Motion](https://mlsanity.com/paper/2202.04901/) (2022)

## Built on by (most cited first, 1 of 1)

- [DUET: A Diversity-Quality Duet of Distillation Experts for Two-Step Video Generation](https://mlsanity.com/paper/2608.09637/) (2026)

## Abstract (arXiv)

How can we tell whether a video has been sped up or slowed down? How can we generate videos at different speeds? Although videos have been central to modern computer vision research, little attention has been paid to perceiving and controlling the passage of time. In this paper, we study time as a learnable visual concept and develop models for reasoning about and manipulating the flow of time in videos. We first exploit the multimodal cues and temporal structure naturally present in videos to learn, in a self-supervised manner, to detect speed changes and estimate playback speed. We then show that these learned temporal reasoning models enable us to curate the largest slow-motion video dataset to date from noisy in-the-wild sources. Such slow-motion footage, typically filmed by high-speed cameras, contains substantially richer temporal detail than standard videos. Using this data, we further develop models capable of temporal control, including speed-conditioned video generation, which produces motion at specified playback speed, and temporal super-resolution, which tranforms low-FPS, blurry videos into high-FPS sequences with fine-grained temporal details. Our findings highlight time as a manipulable, perceptual dimension in video learning, opening doors to temporally controllable video generation, temporal forensics detection, and potentially richer world-models that understand how events unfold over time.