Self-Selective Context for Interaction Recognition

Human-object interaction recognition aims for identifying the relationship between a human subject and an object. Researchers incorporate global scene context into the early layers of deep Convolutional Neural Networks as a solution. They report a significant increase in the performance since generally interactions are correlated with the scene (\ie riding bicycle on the city street). However, this approach leads to the following problems. It increases the network size in the early layers, therefore not efficient. It leads to noisy filter responses when the scene is irrelevant, therefore not accurate. It only leverages scene context whereas human-object interactions offer a multitude of contexts, therefore incomplete. To circumvent these issues, in this work, we propose Self-Selective Context (SSC). SSC operates on the joint appearance of human-objects and context to bring the most discriminative context(s) into play for recognition. We devise novel contextual features that model the locality of human-object interactions and show that SSC can seamlessly integrate with the State-of-the-art interaction recognition models. Our experiments show that SSC leads to an important increase in interaction recognition performance, while using much fewer parameters.

[1]  Andrew Zisserman,et al.  Two-Stream Convolutional Networks for Action Recognition in Videos , 2014, NIPS.

[2]  Jitendra Malik,et al.  Actions and Attributes from Wholes and Parts , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[3]  Bolei Zhou,et al.  Semantic Understanding of Scenes Through the ADE20K Dataset , 2016, International Journal of Computer Vision.

[4]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[5]  Eiichi Yoshida,et al.  Human-Robot Cooperation Based on Interaction Learning , 2010, From Motor Learning to Interaction Learning in Robots.

[6]  Charles C. Kemp,et al.  Human-Robot Interaction for Cooperative Manipulation: Handing Objects to One Another , 2007, RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication.

[7]  Cewu Lu,et al.  RMPE: Regional Multi-person Pose Estimation , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[8]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[9]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Svetlana Lazebnik,et al.  Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering , 2016, ECCV.

[11]  Cewu Lu,et al.  Pairwise Body-Part Attention for Recognizing Human-Object Interactions , 2018, ECCV.

[12]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[13]  Bolei Zhou,et al.  Places: A 10 Million Image Database for Scene Recognition , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[15]  Vittorio Ferrari,et al.  COCO-Stuff: Thing and Stuff Classes in Context , 2016, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Krista A. Ehinger,et al.  SUN database: Large-scale scene recognition from abbey to zoo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Limin Wang,et al.  Computer Vision and Image Understanding Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice , 2022 .

[18]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[19]  Xiaofeng Tao,et al.  Transient attributes for high-level understanding and editing of outdoor scenes , 2014, ACM Trans. Graph..

[20]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Jitendra Malik,et al.  Visual Semantic Role Labeling , 2015, ArXiv.

[22]  Jiaxuan Wang,et al.  HICO: A Benchmark for Recognizing Human-Object Interactions in Images , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[23]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[24]  Sergey Levine,et al.  One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning , 2018, Robotics: Science and Systems.

[25]  Simao Herdade,et al.  Image Captioning: Transforming Objects into Words , 2019, NeurIPS.

[26]  Yoshua Bengio,et al.  Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation , 2013, ArXiv.

[27]  Jitendra Malik,et al.  Contextual Action Recognition with R*CNN , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[28]  Jia Deng,et al.  Learning to Detect Human-Object Interactions , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[29]  Kaiming He,et al.  Detecting and Recognizing Human-Object Interactions , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.