Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst being consistent throughout the frames. Creating a benchmark for video generation requires data annotated over time, which contrasts with the single caption used often in video datasets. To fill this gap, we collect comprehensive human annotations on three existing datasets, and introduce StoryBench: a new, challenging multi-task benchmark to reliably evaluate forthcoming text-to-video models. Our benchmark includes three video generation tasks of increasing difficulty: action execution, where the next action must be generated starting from a conditioning video; story continuation, where a sequence of actions must be executed starting from a conditioning video; and story generation, where a video must be generated from only text prompts. We evaluate small yet strong text-to-video baselines, and show the benefits of training on story-like data algorithmically generated from existing video captions. Finally, we establish guidelines for human evaluation of video stories, and reaffirm the need of better automatic metrics for video generation. StoryBench aims at encouraging future research efforts in this exciting new area.

A deep generative model that describes human motions can benefit a wide range of fundamental computer vision and graphics tasks, such as providing robustness to video-based human pose estimation, predicting complete body movements for motion capture systems during occlusions, and assisting key frame animation with plausible movements. In this paper, we present a method for learning complex human motions independent of specific tasks using a combined global and local latent space to facilitate coarse and fine-grained modeling. Specifically, we propose a hierarchical motion variational autoencoder (HM-VAE) that consists of a 2-level hierarchical latent space. While the global latent space captures the overall global body motion, the local latent space enables to capture the refined poses of the different body parts. We demonstrate the effectiveness of our hierarchical motion variational autoencoder in a variety of tasks including video-based human pose estimation, motion completion from partial observations, and motion synthesis from sparse key-frames. Even though, our model has not been trained for any of these tasks specifically, it provides superior performance than task-specific alternatives. Our general-purpose human motion prior model can fix corrupted human body animations and generate complete movements from incomplete observations.

A long-standing goal in computer vision is to capture, model, and realistically synthesize human behavior. Specifically, by learning from data, our goal is to enable virtual humans to navigate within cluttered indoor scenes and naturally interact with objects. Such embodied behavior has applications in virtual reality, computer games, and robotics, while synthesized behavior can be used as training data. The problem is challenging because real human motion is diverse and adapts to the scene. For example, a person can sit or lie on a sofa in many places and with varying styles. We must model this diversity to synthesize virtual humans that realistically perform human-scene interactions. We present a novel data-driven, stochastic motion synthesis method that models different styles of performing a given action with a target object. Our Scene-Aware Motion Prediction method (SAMP) generalizes to target objects of various geometries while enabling the character to navigate in cluttered scenes. To train SAMP, we collected MoCap data covering various sitting, lying down, walking, and running styles. We demonstrate SAMP on complex indoor scenes and achieve superior performance than existing solutions. Code and data are available for research at https://samp.is.tue.mpg.de.

This paper introduces a motion retargeting method that preserves self-contacts and prevents interpenetration. Self-contacts, such as when hands touch each other or the torso or the head, are important attributes of human body language and dynamics, yet existing methods do not model or preserve these contacts. Likewise, interpenetration, such as a hand passing into the torso, are a typical artifact of motion estimation methods. The input to our method is a human motion sequence and a target skeleton and character geometry. The method identifies self-contacts and ground contacts in the input motion, and optimizes the motion to apply to the output skeleton, while preserving these contacts and reducing interpenetration. We introduce a novel geometry-conditioned recurrent network with an encoder-space optimization strategy that achieves efficient retargeting while satisfying contact constraints. In experiments, our results quantitatively outperform previous methods and we conduct a user study where our retargeted motions are rated as higher-quality than those produced by recent works. We also show our method generalizes to motion estimated from human videos where we improve over previous works that produce noticeable interpenetration.

Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especially in image-based domains. We propose the Deep Planning Network (PlaNet), a purely model-based agent that learns the environment dynamics from images and chooses actions through fast online planning in latent space. To achieve high performance, the dynamics model must accurately predict the rewards ahead for multiple time steps. We approach this using a latent dynamics model with both deterministic and stochastic transition components. Moreover, we propose a multi-step variational inference objective that we name latent overshooting. Using only pixel observations, our agent solves continuous control tasks with contact dynamics, partial observability, and sparse rewards, which exceed the difficulty of tasks that were previously solved by planning with learned models. PlaNet uses substantially fewer episodes and reaches final performance close to and sometimes higher than strong model-free algorithms.

Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics model of the keypoints. Future frames are reconstructed from the keypoints and a reference frame. By modeling dynamics in the keypoint coordinate space, we achieve stable learning and avoid compounding of errors in pixel space. Our method improves upon unstructured representations both for pixel-level video prediction and for downstream tasks requiring object-level understanding of motion dynamics. We evaluate our model on diverse datasets: a multi-agent sports dataset, the Human3.6M dataset, and datasets based on continuous control tasks from the DeepMind Control Suite. The spatially structured representation outperforms unstructured representations on a range of motion-related tasks such as object tracking, action recognition and reward prediction.

Predicting future video frames is extremely challenging, as there are many factors of variation that make up the dynamics of how frames change through time. Previously proposed solutions require complex inductive biases inside network architectures with highly specialized computation, including segmentation masks, optical flow, and foreground and background separation. In this work, we question if such handcrafted architectures are necessary and instead propose a different approach: finding minimal inductive bias for video prediction while maximizing network capacity. We investigate this question by performing the first large-scale empirical study and demonstrate state-of-the-art performance by learning large models on three different datasets: one for modeling object interactions, one for modeling human motion, and one for modeling car driving.

We propose a recurrent neural network architecture with a Forward Kinematics layer and cycle consistency based adversarial training objective for unsupervised motion retargetting. Our network captures the high-level properties of an input motion by the forward kinematics layer, and adapts them to a target character with different skeleton bone lengths (e.g., shorter, longer arms etc.). Collecting paired motion training sequences from different characters is expensive. Instead, our network utilizes cycle consistency to learn to solve the Inverse Kinematics problem in an unsupervised manner. Our method works online, i.e., it adapts the motion sequence on-the-fly as new frames are received. In our experiments, we use the Mixamo animation data1 to test our method for a variety of motions and characters and achieve state-of-the-art results. We also demonstrate motion retargetting from monocular human videos to 3D characters using an off-the-shelf 3D pose estimator.

Much of recent research has been devoted to video prediction and generation, yet most of the previous works have demonstrated only limited success in generating videos on short-term horizons. The hierarchical video prediction method by Villegas et al. (2017) is an example of a state-of-the-art method for long-term video prediction, but their method is limited because it requires ground truth annotation of high-level structures (e.g., human joint landmarks) at training time. Our network encodes the input frame, predicts a high-level encoding into the future, and then a decoder with access to the first frame produces the predicted image from the predicted encoding. The decoder also produces a mask that outlines the predicted foreground object (e.g., person) as a by-product. Unlike Villegas et al. (2017), we develop a novel training method that jointly trains the encoder, the predictor, and the decoder together without highlevel supervision; we further improve upon this by using an adversarial loss in the feature space to train the predictor. Our method can predict about 20 seconds into the future and provides better results compared to Denton and Fergus (2018) and Finn et al. (2016) on the Human 3.6M dataset.

We propose a hierarchical approach for making long-term predictions of future frames. To avoid inherent compounding errors in recursive pixel-level prediction, we propose to first estimate high-level structure in the input frames, then predict how that structure evolves in the future, and finally by observing a single frame from the past and the predicted high-level structure, we construct the future frames without having to observe any of the pixel-level predictions. Long-term video prediction is difficult to perform by recurrently observing the predicted frames because the small errors in pixel space exponentially amplify as predictions are made deeper into the future. Our approach prevents pixel-level error propagation from happening by removing the need to observe the predicted frames. Our model is built with a combination of LSTM and analogy based encoder-decoder convolutional neural networks, which independently predict the video structure and generate the future frames, respectively. In experiments, our model is evaluated on the Human3.6M and Penn Action datasets on the task of long-term pixel-level video prediction of humans performing actions and demonstrate significantly better results than the state-of-the-art.

Object detection systems based on the deep convolutional neural network (CNN) have recently made ground-breaking advances on several object detection benchmarks. While the features learned by these high-capacity neural networks are discriminative for categorization, inaccurate localization is still a major source of error for detection. Building upon high-capacity CNN architectures, we address the localization problem by 1) using a search algorithm based on Bayesian optimization that sequentially proposes candidate regions for an object bounding box, and 2) training the CNN with a structured loss that explicitly penalizes the localization inaccuracy. In experiments, we demonstrate that each of the proposed methods improves the detection performance over the baseline method on PASCAL VOC 2007 and 2012 datasets. Furthermore, two methods are complementary and significantly outperform the previous state-of-the-art when combined.

Recent years have seen a major push for face recognition technology due to the large expansion of image sharing on social networks. In this paper, we consider the difficult task of determining parent-offspring resemblance using deep learning to answer the question "Who do I look like?" Although humans can perform this job at a rate higher than chance, it is not clear how they do it [2]. However, recent studies in anthropology [24] have determined which features tend to be the most discriminative. In this study, we aim to not only create an accurate system for resemblance detection, but bridge the gap between studies in anthropology with computer vision techniques. Further, we aim to answer two key questions: 1) Do offspring resemble their parents? and 2) Do offspring resemble one parent more than the other? We propose an algorithm that fuses the features and metrics discovered via gated autoencoders with a discriminative neural network layer that learns the optimal, or what we call genetic, features to delineate parent-offspring relationships. We further analyze the correlation between our automatically detected features and those found in anthropological studies. Meanwhile, our method outperforms the state-of-the-art in kinship verification by 3-10% depending on the relationship using specific (father-son, mother-daughter, etc.) and generic models.