Estimating the 3D pose of a hand is an essential part of human-computer interaction. Estimating 3D pose using depth or multi-view sensors has become easier with recent advances in computer vision, however, regressing pose from a single RGB image is much less straightforward. The main difficulty arises from the fact that 3D pose requires some form of depth estimates, which are ambiguous given only an RGB image. In this paper we propose a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation. Our new representation estimates pose up to a scaling factor, which can be estimated additionally if a prior of the hand size is given. We implicitly learn depth maps and heatmap distributions with a novel CNN architecture. Our system achieves the state-of-the-art estimation of 2D and 3D hand pose on several challenging datasets in presence of severe occlusions.
Human poses and motions are important cues for analysis of videos with people and there is strong evidence that representations based on body pose are highly effective for a variety of tasks such as activity recognition, content retrieval and social signal processing. In this work, we aim to further advance the state of the art by establishing "PoseTrack", a new large-scale benchmark for video-based human pose estimation and articulated tracking, and bringing together the community of researchers working on visual human analysis. The benchmark encompasses three competition tracks focusing on i) single-frame multi-person pose estimation, ii) multi-person pose estimation in videos, and iii) multi-person articulated tracking. To facilitate the benchmark and challenge we collect, annotate and release a new %large-scale benchmark dataset that features videos with multiple people labeled with person tracks and articulated pose. A centralized evaluation server is provided to allow participants to evaluate on a held-out test set. We envision that the proposed benchmark will stimulate productive research both by providing a large and representative training dataset as well as providing a platform to objectively evaluate and compare the proposed methods. The benchmark is freely accessible at https://posetrack.net.
Analyzing human actions in videos has gained increased attention recently. While most works focus on classifying and labeling observed video frames or anticipating the very recent future, making long-term predictions over more than just a few seconds is a task with many practical applications that has not yet been addressed. In this paper, we propose two methods to predict a considerably large amount of future actions and their durations. Both, a CNN and an RNN are trained to learn future video labels based on previously seen content. We show that our methods generate accurate predictions of the future even for long videos with a huge amount of different actions and can even deal with noisy or erroneous input information.
A group of persons can be analyzed at various semantic levels such as individual actions, their interactions, and the activity of the entire group. In this paper, we propose a structural recurrent neural network (SRNN) that uses a series of interconnected RNNs to jointly capture the actions of individuals, their interactions, as well as the group activity. While previous structural recurrent neural networks assumed that the number of nodes and edges is constant, we use a grid pooling layer to address the fact that the number of individuals in a group can vary. We evaluate two variants of the structural recurrent neural network on the Volleyball Dataset.
We question the dominant role of real-world training images in the field of material classification by investigating whether synthesized data can generalise more effectively than real-world data. Experimental results on three challenging real-world material databases show that the best performing pre-trained convolutional neural network (CNN) architectures can achieve up to 91.03% mean average precision when classifying materials in cross-dataset scenarios. We demonstrate that synthesized data achieve an improvement on mean average precision when used as training data and in conjunction with pre-trained CNN architectures, which spans from ~ 5% to ~ 19% across three widely used material databases of real-world images.
We present an approach for weakly supervised learning of human actions. Given a set of videos and an ordered list of the occurring actions, the goal is to infer start and end frames of the related action classes within the video and to train the respective action classifiers without any need for hand labeled frame boundaries. To address this task, we propose a combination of a discriminative representation of subactions, modeled by a recurrent neural network, and a coarse probabilistic model to allow for a temporal alignment and inference over long sequences. While this system alone already generates good results, we show that the performance can be further improved by approximating the number of subactions to the characteristics of the different action classes. To this end, we adapt the number of subaction classes by iterating realignment and reestimation during training. The proposed system is evaluated on two benchmark datasets, the Breakfast and the Hollywood extended dataset, showing a competitive performance on various weak learning tasks such as temporal action segmentation and action alignment.
In this work we address the challenging problem of 3D human pose estimation from single images. Recent approaches learn deep neural networks to regress 3D pose directly from images. One major challenge for such methods, however, is the collection of training data. Specifically, collecting large amounts of training data containing unconstrained images annotated with accurate 3D poses is infeasible. We therefore propose to use two independent training sources. The first source consists of accurate 3D motion capture data, and the second source consists of unconstrained images with annotated 2D poses. To integrate both sources, we propose a dual-source approach that combines 2D pose estimation with efficient 3D pose retrieval. To this end, we first convert the motion capture data into a normalized 2D pose space, and separately learn a 2D pose estimation model from the image data. During inference, we estimate the 2D pose and efficiently retrieve the nearest 3D poses. We then jointly estimate a mapping from the 3D pose space to the image and reconstruct the 3D pose. We provide a comprehensive evaluation of the proposed method and experimentally demonstrate the effectiveness of our approach, even when the skeleton structures of the two sources differ substantially.
This paper proposes an end-to-end learning framework for multiview stereopsis. We term the network SurfaceNet. It takes a set of images and their corresponding camera parameters as input and directly infers the 3D model. The key advantage of the framework is that both photo-consistency as well geometric relations of the surface structure can be directly learned for the purpose of multiview stereopsis in an end-to-end fashion. SurfaceNet is a fully 3D convolutional network which is achieved by encoding the camera parameters together with the images in a 3D voxel representation. We evaluate SurfaceNet on the large-scale DTU benchmark.
The concept of affordance is important to understand the relevance of object parts for a certain functional interaction. Affordance types generalize across object categories and are not mutually exclusive. This makes the segmentation of affordance regions of objects in images a difficult task. In this work, we build on an iterative approach that learns a convolutional neural network for affordance segmentation from sparse keypoints. During this process, the predictions of the network need to be binarized. In this work, we propose an adaptive approach for binarization and estimate the parameters for initialization by approximated cross validation. We evaluate our approach on two affordance datasets where our approach outperforms the state-of-the-art for weakly supervised affordance segmentation.
Action recognition is a fundamental problem in computer vision with a lot of potential applications such as video surveillance, human computer interaction, and robot learning. Given pre-segmented videos, the task is to recognize actions happening within videos. Historically, hand crafted video features were used to address the task of action recognition. With the success of Deep ConvNets as an image analysis method, a lot of extensions of standard ConvNets were purposed to process variable length video data. In this work, we propose a novel recurrent ConvNet architecture called recurrent residual networks to address the task of action recognition. The approach extends ResNet, a state of the art model for image classification. While the original formulation of ResNet aims at learning spatial residuals in its layers, we extend the approach by introducing recurrent connections that allow to learn a spatio-temporal residual. In contrast to fully recurrent networks, our temporal connections only allow a limited range of preceding frames to contribute to the output for the current frame, enabling efficient training and inference as well as limiting the temporal context to a reasonable local range around each frame. On a large-scale action recognition dataset, we show that our model improves over both, the standard ResNet architecture and a ResNet extended by a fully recurrent layer.