We propose a new challenging task: procedure planning in instructional videos. Unlike existing planning problems, where both the state and the action spaces are well-defined, the key challenge of planning in instructional videos is that both the state and the action spaces are open-vocabulary. We address this challenge with latent space planning, where we propose to explicitly leverage the constraints imposed by the conjugate relationships between states and actions in a learned plannable latent space. We evaluate both procedure planning and walkthrough planning on large-scale real-world instructional videos. Our experiments show that we are able to learn plannable semantic representations without explicit supervision. This enables sequential reasoning on real-world videos and leads to stronger generalization compared to existing planning approaches and neural network policies.
There is a growing interest in learning a model which could recognize novel classes with only a few labeled examples. In this paper, we propose Temporal Alignment Module (TAM), a novel few-shot learning framework that can learn to classify a previous unseen video. While most previous works neglect long-term temporal ordering information, our proposed model explicitly leverages the temporal ordering information in video data through temporal alignment. This leads to strong data-efficiency for few-shot learning. In concrete, TAM calculates the distance value of query video with respect to novel class proxies by averaging the per frame distances along its alignment path. We introduce continuous relaxation to TAM so the model can be learned in an end-to-end fashion to directly optimize the few-shot learning objective. We evaluate TAM on two challenging real-world datasets, Kinetics and Something-Something-V2, and show that our model leads to significant improvement of few-shot video classification over a wide range of competitive baselines.
Predicting the future is an important aspect for decision-making in robotics or autonomous driving systems, which heavily rely upon visual scene understanding. While prior work attempts to predict future video pixels, anticipate activities or forecast future scene semantic segments from segmentation of the preceding frames, methods that predict future semantic segmentation solely from the previous frame RGB data in a single end-to-end trainable model do not exist. In this paper, we propose a temporal encoder-decoder network architecture that encodes RGB frames from the past and decodes the future semantic segmentation. The network is coupled with a new knowledge distillation training framework specifically for the forecasting task. Our method, only seeing preceding video frames, implicitly models the scene segments while simultaneously accounting for the object dynamics to infer the future scene semantic segments. Our results on Cityscapes outperform the baseline and current state-of-the-art methods. Code is available at https://github.com/eddyhkchiu/segmenting_the_future/.
Deciphering human behaviors to predict their future paths/trajectories and what they would do from videos is important in many applications. Motivated by this idea, this paper studies predicting a pedestrian's future path jointly with future activities. We propose an end-to-end, multi-task learning system utilizing rich visual features about human behavioral information and interaction with their surroundings. To facilitate the training, the network is learned with an auxiliary task of predicting future location in which the activity will happen. Experimental results demonstrate our state-of-the-art performance over two public benchmarks on future trajectory prediction. Moreover, our method is able to produce meaningful future activity prediction in addition to the path. The result provides the first empirical evidence that joint modeling of paths and activities benefits future path prediction.
Our goal is to generate a policy to complete an unseen task given just a single video demonstration of the task in a given domain. We hypothesize that to successfully generalize to unseen complex tasks from a single video demonstration, it is necessary to explicitly incorporate the compositional structure of the tasks into the model. To this end, we propose Neural Task Graph (NTG) Networks, which use conjugate task graph as the intermediate representation to modularize both the video demonstration and the derived policy. We empirically show NTG achieves inter-task generalization on two complex tasks: Block Stacking in BulletPhysics and Object Collection in AI2-THOR. NTG improves data efficiency with visual input as well as achieve strong generalization without the need for dense hierarchical supervision. We further show that similar performance trends hold when applied to real-world data. We show that NTG can effectively predict task structure on the JIGSAWS surgical dataset and generalize to unseen tasks.
We address weakly-supervised action alignment and segmentation in videos, where only the order of occurring actions is available during training. We propose Discriminative Differentiable Dynamic Time Warping (D${}^3$TW), which is the first discriminative model for weak ordering supervision. This allows us to bypass the degenerated sequence problem usually encountered in previous work. The key technical challenge for discriminative modeling with weak-supervision is that the loss function of the ordering supervision is usually formulated using dynamic programming and is thus not differentiable. We address this challenge by continuous relaxation of the min-operator in dynamic programming and extend the DTW alignment loss to be differentiable. The proposed D${}^3$TW innovatively solves sequence alignment with discriminative modeling and end-to-end training, which substantially improves the performance in weakly supervised action alignment and segmentation tasks. We show that our model outperforms the current state-of-the-art across three evaluation metrics in two challenging datasets.
Predicting and forecasting human dynamics is a very interesting but challenging task with several prospective applications in robotics, health-care, etc. Recently, several methods have been developed for human pose forecasting; however, they often introduce a number of limitations in their settings. For instance, previous work either focused only on short-term or long-term predictions, while sacrificing one or the other. Furthermore, they included the activity labels as part of the training process, and require them at testing time. These limitations confine the usage of pose forecasting models for real-world applications, as often there are no activity-related annotations for testing scenarios. In this paper, we propose a new action-agnostic method for short- and long-term human pose forecasting. To this end, we propose a new recurrent neural network for modeling the hierarchical and multi-scale characteristics of the human dynamics, denoted by triangular-prism RNN (TP-RNN). Our model captures the latent hierarchical structure embedded in temporal human pose sequences by encoding the temporal dependencies with different time-scales. For evaluation, we run an extensive set of experiments on Human 3.6M and Penn Action datasets and show that our method outperforms baseline and state-of-the-art methods quantitatively and qualitatively. Codes are available at https://github.com/eddyhkchiu/pose_forecast_wacv/
Our goal is to predict future video frames given a sequence of input frames. Despite large amounts of video data, this remains a challenging task because of the high-dimensionality of video frames. We address this challenge by proposing the Decompositional Disentangled Predictive Auto-Encoder (DDPAE), a framework that combines structured probabilistic models and deep networks to automatically (i) decompose the high-dimensional video that we aim to predict into components, and (ii) disentangle each component to have low-dimensional temporal dynamics that are easier to predict. Crucially, with an appropriately specified generative model of video frames, our DDPAE is able to learn both the latent decomposition and disentanglement without explicit supervision. For the Moving MNIST dataset, we show that DDPAE is able to recover the underlying components (individual digits) and disentanglement (appearance and location) as we would intuitively do. We further demonstrate that DDPAE can be applied to the Bouncing Balls dataset involving complex interactions between multiple objects to predict the video frame directly from the pixels and recover physical states without explicit supervision.
We propose an end-to-end deep learning model for translating free-form natural language instructions to a high-level plan for behavioral robot navigation. We use attention models to connect information from both the user instructions and a topological representation of the environment. We evaluate our model's performance on a new dataset containing 10,050 pairs of navigation instructions. Our model significantly outperforms baseline approaches. Furthermore, our results suggest that it is possible to leverage the environment map as a relevant knowledge base to facilitate the translation of free-form navigational instruction.