Benchmarks
Datasets
Greatest papers with code
Improving Video Generation for Multi-functional Applications
• bernhard2202/improved-video-gan
• 
In this paper, we aim to improve the state-of-the-art video generative adversarial networks (GANs) with a view towards multi-functional applications.
COLORIZATION FUTURE PREDICTION VIDEO GENERATION VIDEO INPAINTING
Peeking into the Future: Predicting Future Person Activities and Locations in Videos
CVPR 2019
• google/next-prediction
•
To facilitate the training, the network is learned with an auxiliary task of predicting future location in which the activity will happen.
Ranked #1 on
Trajectory Forecasting
on ActEV
ACTIVITY PREDICTION FUTURE PREDICTION HUMAN MOTION PREDICTION MOTION FORECASTING MULTI-TASK LEARNING TRAJECTORY FORECASTING
Decomposing Motion and Content for Natural Video Sequence Prediction
• rubenvillegas/iclr2017mcnet
•
To the best of our knowledge, this is the first end-to-end trainable network architecture with motion and content separation to model the spatiotemporal dynamics for pixel-level future prediction in natural videos.
Predicting 3D Human Dynamics from Video
In this work, we present perhaps the first approach for predicting a future 3D mesh model sequence of a person from past video input.
3D HUMAN DYNAMICS 3D HUMAN POSE ESTIMATION FUTURE PREDICTION LANGUAGE MODELLING
Interpreting Tree Ensembles with inTrees
Tree ensembles such as random forests and boosted trees are accurate but difficult to understand, debug and deploy.
Compositional Video Prediction
ICCV 2019
• JudyYe/CVP
• 
We present an approach for pixel-level future prediction given an input image of a scene.
Data-Efficient Reinforcement Learning with Self-Predictive Representations
We further improve performance by adding data augmentation to the future prediction loss, which forces the agent's representations to be consistent across multiple views of an observation.
DATA AUGMENTATION FUTURE PREDICTION GENERAL REINFORCEMENT LEARNING SELF-SUPERVISED LEARNING
DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
DESIRE effectively predicts future locations of objects in multiple scenes by 1) accounting for the multi-modal nature of the future prediction (i. e., given the same context, future may vary), 2) foreseeing the potential future outcomes and make a strategic prediction based on that, and 3) reasoning not only from the past motion history, but also from the scene context as well as the interactions among the agents.
Ranked #1 on
Trajectory Prediction
on PAID
Deep RNN Framework for Visual Sequential Applications
CVPR 2019
• BoPang1996/Deep-RNN-Framework
•
There are mainly two novel designs in our deep RNN framework: one is a new RNN module called Context Bridge Module (CBM) which splits the information flowing along the sequence (temporal direction) and along depth (spatial representation direction), making it easier to train when building deep by balancing these two directions; the other is the Overlap Coherence Training Scheme that reduces the training complexity for long visual sequential tasks on account of the limitation of computing resources.
INFER: INtermediate representations for FuturE pRediction
• talsperre/INFER
•
Uncharacteristic of state-of-the-art approaches, our representations and models generalize to completely different datasets, collected across several cities, and also across countries where people drive on opposite sides of the road (left-handed vs right-handed driving).
ACTIVITY PREDICTION FUTURE PREDICTION MULTI-OBJECT TRACKING TRAJECTORY PREDICTION