skip to main content

Title: Forecasting Action through Contact Representations from First Person Video
Human visual understanding of action is reliant on anticipation of contact as is demonstrated by pioneering work in cognitive science. Taking inspiration from this, we introduce representations and models centered on contact, which we then use in action prediction and anticipation. We annotate a subset of the EPIC Kitchens dataset to include time-to-contact between hands and objects, as well as segmentations of hands and objects. Using these annotations we train the Anticipation Module, a module producing Contact Anticipation Maps and Next Active Object Segmentations - novel low-level representations providing temporal and spatial characteristics of anticipated near future action. On top of the Anticipation Module we apply Egocentric Object Manipulation Graphs (Ego-OMG), a framework for action anticipation and prediction. Ego-OMG models longer-term temporal semantic relations through the use of a graph modeling transitions between contact delineated action states. Use of the Anticipation Module within Ego-OMG produces state-of-the-art results, achieving 1st and 2nd place on the unseen and seen test sets, respectively, of the EPIC Kitchens Action Anticipation Challenge, and achieving state-of-the-art results on the tasks of action anticipation and action prediction over EPIC Kitchens. We perform ablation studies over characteristics of the Anticipation Module to evaluate their utility.
; ; ; ;
Award ID(s):
Publication Date:
Journal Name:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Sponsoring Org:
National Science Foundation
More Like this
  1. In this paper we learn to segment hands and hand-held objects from motion. Our system takes a single RGB image and hand location as input to segment the hand and hand-held object. For learning, we generate responsibility maps that show how well a hand’s motion explains other pixels’ motion in video. We use these responsibility maps as pseudo-labels to train a weakly-supervised neural network using an attention-based similarity loss and contrastive loss. Our system outperforms alternate methods, achieving good performance on the 100DOH, EPIC-KITCHENS, and HO3D datasets.
  2. Modelling and learning the dynamics of intricate dynamic interactions prevalent in common tasks such as push- ing a heavy door or picking up an object in one sweeping motion is a challenging problem. One needs to consider both the dynamics of the individual objects and of the interactions among objects. In this work, we present a method that enables efficient learning of the dynamics of interacting systems by simultaneously learning a dynamic graph structure and a stable and locally linear forward dynamic model of the system. The dynamic graph structure encodes evolving contact modes along a trajectory by making probabilistic predictions over the edge activations. Introducing a temporal dependence in the learned graph structure enables incorporating contact measurement updates which allows for more accurate forward predictions. The learned stable and locally linear dynamics enable the use of optimal control algorithms such as iLQR for long-horizon planning and control for complex interactive tasks. Through experiments in simulation and in the real world, we evaluate the performance of our method by using the learned inter- action dynamics for control and demonstrate generalization to more objects and interactions not seen during training. We also introduce a control scheme that takes advantage of contactmore »measurement updates and hence is robust to prediction inaccuracies during execution.« less
  3. Detecting small objects (e.g., manhole covers, license plates, and roadside milestones) in urban images is a long-standing challenge mainly due to the scale of small object and background clutter. Although convolution neural network (CNN)-based methods have made significant progress and achieved impressive results in generic object detection, the problem of small object detection remains unsolved. To address this challenge, in this study we developed an end-to-end network architecture that has three significant characteristics compared to previous works. First, we designed a backbone network module, namely Reduced Downsampling Network (RD-Net), to extract informative feature representations with high spatial resolutions and preserve local information for small objects. Second, we introduced an Adjustable Sample Selection (ADSS) module which frees the Intersection-over-Union (IoU) threshold hyperparameters and defines positive and negative training samples based on statistical characteristics between generated anchors and ground reference bounding boxes. Third, we incorporated the generalized Intersection-over-Union (GIoU) loss for bounding box regression, which efficiently bridges the gap between distance-based optimization loss and area-based evaluation metrics. We demonstrated the effectiveness of our method by performing extensive experiments on the public Urban Element Detection (UED) dataset acquired by Mobile Mapping Systems (MMS). The Average Precision (AP) of the proposed method was 81.71%,more »representing an improvement of 1.2% compared with the popular detection framework Faster R-CNN.« less
  4. While current vision algorithms excel at many challenging tasks, it is unclear how well they understand the physical dynamics of real-world environments. Here we introduce Physion, a dataset and benchmark for rigorously evaluating the ability to predict how physical scenarios will evolve over time. Our dataset features realistic simulations of a wide range of physical phenomena, including rigid and soft-body collisions, stable multi-object configurations, rolling, sliding, and projectile motion, thus providing a more comprehensive challenge than previous benchmarks. We used Physion to benchmark a suite of models varying in their architecture, learning objective, input-output structure, and training data. In parallel, we obtained precise measurements of human prediction behavior on the same set of scenarios, allowing us to directly evaluate how well any model could approximate human behavior. We found that vision algorithms that learn object-centric representations generally outperform those that do not, yet still fall far short of human performance. On the other hand, graph neural networks with direct access to physical state information both perform substantially better and make predictions that are more similar to those made by humans. These results suggest that extracting physical representations of scenes is the main bottleneck to achieving human-level and human-like physical understandingmore »in vision algorithms. We have publicly released all data and code to facilitate the use of Physion to benchmark additional models in a fully reproducible manner, enabling systematic evaluation of progress towards vision algorithms that understand physical environments as robustly as people do.« less
  5. Vedaldi, A. ; Bischof, H. ; Brox, T. ; Frahm, JM. (Ed.)
    The problem of action localization involves locating the action in the video, both over time and spatially in the image. The current dominant approaches use supervised learning to solve this problem. They require large amounts of annotated training data, in the form of frame-level bounding box annotations around the region of interest. In this paper, we present a new approach based on continual learning that uses feature-level predictions for self-supervision. It does not require any training annotations in terms of frame-level bounding boxes. The approach is inspired by cognitive models of visual event perception that propose a prediction-based approach to event understanding. We use a stack of LSTMs coupled with a CNN encoder, along with novel attention mechanisms, to model the events in the video and use this model to predict high-level features for the future frames. The prediction errors are used to learn the parameters of the models continuously. This self-supervised framework is not complicated as other approaches but is very effective in learning robust visual representations for both labeling and localization. It should be noted that the approach outputs in a streaming fashion, requiring only a single pass through the video, making it amenable for real-time processing. Wemore »demonstrate this on three datasets - UCF Sports, JHMDB, and THUMOS’13 and show that the proposed approach outperforms weakly-supervised and unsupervised baselines and obtains competitive performance compared to fully supervised baselines. Finally, we show that the proposed framework can generalize to egocentric videos and achieve state-of-the-art results on the unsupervised gaze prediction task.« less