An official website of the United States government
Human pose estimation (HPE) is inherently a homogeneous multi-task learning problem, with the localization of each body part as a different task. Recent HPE approaches universally learn a shared representation for all parts, from which their locations are linearly regressed. However, our statistical analysis indicates not all parts are related to each other. As a result, such a sharing mechanism can lead to negative transfer and deteriorate the performance. This potential issue drives us to raise an interesting question. Can we identify related parts and learn specific features for them to improve pose estimation? Since unrelated tasks no longer share a high-level representation, we expect to avoid the adverse effect of negative transfer. In addition, more explicit structural knowledge, e.g., ankles and knees are highly related, is incorporated into the model, which helps resolve ambiguities in HPE. To answer this question, we first propose a data-driven approach to group related parts based on how much information they share. Then a part-based branching network (PBN) is introduced to learn representations specific to each part group. We further present a multi-stage version of this network to repeatedly refine intermediate features and pose estimates. Ablation experiments indicate learning specific features significantly improves the localization of occluded parts and thus benefits HPE. Our approach also outperforms all state-of-the-art methods on two benchmark datasets, with an outstanding advantage when occlusion occurs.
more »
« less
Deeply Learned Compositional Models for Human Pose Estimation
Compositional models represent patterns with hierarchies of meaningful parts and subparts. Their ability to characterize high-order relationships among body parts helps resolve low-level ambiguities in human pose estimation (HPE). However, prior compositional models make unrealistic assumptions on subpart-part relationships, making them incapable to characterize complex compositional patterns. Moreover, state spaces of their higher-level parts can be exponentially large, complicating both inference and learning. To address these issues, this paper introduces a novel framework, termed as Deeply Learned Compositional Model (DLCM), for HPE. It exploits deep neural networks to learn the compositionality of human bodies. This results in a novel network with a hierarchical compositional architecture and bottom-up/top-down inference stages. In addition, we propose a novel bone-based part representation. It not only compactly encodes orientations, scales and shapes of parts, but also avoids their potentially large state spaces. With significantly lower complexities, our approach outperforms state-of-the-art methods on three benchmark datasets.
more »
« less
- Award ID(s):
- 1815561
- PAR ID:
- 10105067
- Date Published:
- Journal Name:
- Proc. of European Conference on Computer Vision
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The graph convolutional network (GCN) has recently achieved promising performance of 3D human pose estimation (HPE) by modeling the relationship among body parts. However, most prior GCN approaches suffer from two main drawbacks. First, they share a feature transformation for each node within a graph convolution layer. This prevents them from learning different relations between different body joints. Second, the graph is usually defined according to the human skeleton and is suboptimal because human activities often exhibit motion patterns beyond the natural connections of body joints. To address these limitations, we introduce a novel Modulated GCN for 3D HPE. It consists of two main components: weight modulation and affinity modulation. Weight modulation learns different modulation vectors for different nodes so that the feature transformations of different nodes are disentangled while retaining a small model size. Affinity modulation adjusts the graph structure in a GCN so that it can model additional edges beyond the human skeleton. We investigate several affinity modulation methods as well as the impact of regularizations. Rigorous ablation study indicates both types of modulation improve performance with negligible overhead. Compared with state-of-the-art GCNs for 3D HPE, our approach either significantly reduces the estimation errors, e.g., by around 10%, while retaining a small model size or drastically reduces the model size, e.g., from 4.22M to 0.29M (a 14.5× reduction), while achieving comparable performance. Results on two benchmarks show our Modulated GCN outperforms some recent states of the art. Our code is available at https://github.com/ZhimingZo/Modulated-GCN.more » « less
-
Deep learning has achieved remarkable results in 3D shape analysis by learning global shape features from the pixel-level over multiple views. Previous methods, however, compute low-level features for entire views without considering part-level information. In contrast, we propose a deep neural network, called Parts4Feature, to learn 3D global features from part-level information in multiple views. We introduce a novel definition of generally semantic parts, which Parts4Feature learns to detect in multiple views from different 3D shape segmentation benchmarks. A key idea of our architecture is that it transfers the ability to detect semantically meaningful parts in multiple views to learn 3D global features. Parts4Feature achieves this by combining a local part detection branch and a global feature learning branch with a shared region proposal module. The global feature learning branch aggregates the detected parts in terms of learned part patterns with a novel multi-attention mechanism, while the region proposal module enables locally and globally discriminative information to be promoted by each other. We demonstrate that Parts4Feature outperforms the state-of-the-art under three large-scale 3D shape benchmarks.more » « less
-
Population genetics has been successful at identifying the relationships between human groups and their interconnected histories. However, the link between genetic demography inferred at large scales and the individual human behaviours that ultimately generate that demography is not always clear. While anthropological and historical context are routinely presented as adjuncts in population genetic studies to help describe the past, determining how underlying patterns of human sociocultural behaviour impact genetics still remains challenging. Here, we analyse patterns of genetic variation in village-scale samples from two islands in eastern Indonesia, patrilocal Sumba and a matrilocal region of Timor. Adopting a ‘process modelling’ approach, we iteratively explore combinations of structurally different models as a thinking tool. We find interconnected socio-genetic interactions involving sex-biased migration, lineage-focused founder effects, and on Sumba, heritable social dominance. Strikingly, founder ideology, a cultural model derived from anthropological and archaeological studies at larger regional scales, has both its origins and impact at the scale of villages. Process modelling lets us explore these complex interactions, first by circumventing the complexity of formal inference when studying large datasets with many interacting parts, and then by explicitly testing complex anthropological hypotheses about sociocultural behaviour from a more familiar population genetic standpoint.more » « less
-
Large-scale neural network models combining text and images have made incredible progress in recent years. However, it remains an open question to what extent such models encode compositional representations of the concepts over which they operate, such as correctly identifying red cube by reasoning over the constituents red and cube. In this work, we focus on the ability of a large pretrained vision and language model (CLIP) to encode compositional concepts and to bind variables in a structure-sensitive way (e.g., differentiating cube behind sphere from sphere behind cube). To inspect the performance of CLIP, we compare several architectures from research on compositional distributional semantics models (CDSMs), a line of research that attempts to implement traditional compositional linguistic structures within embedding spaces. We benchmark them on three synthetic datasets– singleobject, two-object, and relational– designed to test concept binding. We find that CLIP can compose concepts in a single-object setting, but in situations where concept binding is needed, performance drops dramatically. At the same time, CDSMs also perform poorly, with best performance at chance level.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
