RECORD
Construction of Latent Descriptor Space and Inference Model of Hand-Object Interactions
Computer Vision and Pattern Recognition · Submitted 12 Sep 2017
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim And also we demonstrate that the model can infer possible hand-object interactions.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Appearance-based generic object recognition is a challenging problem because all possible appearances of objects cannot be registered, especially as new objects are produced every day. Function of objects, however, has a comparatively small number of prototypes. Therefore, function-based classification of new objects could be a valuable tool for generic object recognition. Object functions are closely related to hand-object interactions during handling of a functional object; i.e., how the hand approaches the object, which parts of the object and contact the hand, and the shape of the hand during interaction. Hand-object interactions are helpful for modeling object functions. However, it is difficult to assign discrete labels to interactions because an object shape and grasping hand-postures intrinsically have continuous variations. To describe these interactions, we propose the interaction descriptor space which is acquired from unlabeled appearances of human hand-object interactions. By using interaction descriptors, we can numerically describe the relation between an object's appearance and its possible interaction with the hand. The model infers the quantitative state of the interaction from the object image alone. It also identifies the parts of objects designed for hand interactions such as grips and handles. We demonstrate that the proposed method can unsupervisedly generate interaction descriptors that make clusters corresponding to interaction types. And also we demonstrate that the model can infer possible hand-object interactions.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Appearance-based generic object recognition is a challenging problem because all possible appearances of objects cannot be registered, especially as new objects are produced every day. | background 1.00 | 0.06 | 0.02 | asserted 1.00 |
| s1 | Function of objects, however, has a comparatively small number of prototypes. | background 1.00 | 0.08 | 0.03 | asserted 0.99 |
| s2 | Therefore, function-based classification of new objects could be a valuable tool for generic object recognition. | background 0.79 | 0.07 | 0.10 | hedged possibility 1.00 |
| s3 | Object functions are closely related to hand-object interactions during handling of a functional object; i.e., how the hand approaches the object, which parts of the object and contact the hand, and the shape of the hand during interaction. | background 1.00 | 0.10 | 0.04 | asserted 1.00 |
| s4 | Hand-object interactions are helpful for modeling object functions. | background 0.99 | 0.09 | 0.07 | asserted 0.96 |
| s5 | However, it is difficult to assign discrete labels to interactions because an object shape and grasping hand-postures intrinsically have continuous variations. | gap 0.62 | 0.10 | 0.02 | asserted 1.00 |
| s6 | To describe these interactions, we propose the interaction descriptor space which is acquired from unlabeled appearances of human hand-object interactions. | method 0.62 | 0.91 | 0.08 | asserted 0.92 |
| s7 | By using interaction descriptors, we can numerically describe the relation between an object's appearance and its possible interaction with the hand. | method 0.80 | 0.70 | 0.10 | asserted 0.55 |
| s8 | The model infers the quantitative state of the interaction from the object image alone. | method 0.68 | 0.81 | 0.13 | asserted 1.00 |
| s9 | It also identifies the parts of objects designed for hand interactions such as grips and handles. | contribution 0.44 | 0.83 | 0.11 | asserted 1.00 |
| s10 | We demonstrate that the proposed method can unsupervisedly generate interaction descriptors that make clusters corresponding to interaction types. | result 0.97 | 0.96 | 0.26 | asserted 1.00 |
| s11 | And also we demonstrate that the model can infer possible hand-object interactions. | result 0.95 | 0.94 | 0.28 | asserted 0.99 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Appearance-based generic object recognition is a challenging problem because all possible appearances of objects cannot be registered, especially as new objects are produced every day. Function of objects, however, has a comparatively small number of prototypes. Therefore, function-based classification of new objects could be a valuable tool for generic object recognition. Object functions are closely related to hand-object interactions during handling of a functional object; i.e., how the hand approaches the object, which parts of the object and contact the hand, and the shape of the hand during interaction. Hand-object interactions are helpful for modeling object functions. However, it is difficult to assign discrete labels to interactions because an object shape and grasping hand-postures intrinsically have continuous variations. To describe these interactions, we propose the interaction descriptor space which is acquired from unlabeled appearances of human hand-object interactions. By using interaction descriptors, we can numerically describe the relation between an object's appearance and its possible interaction with the hand. The model infers the quantitative state of the interaction from the object image alone. It also identifies the parts of objects designed for hand interactions such as grips and handles. We demonstrate that the proposed method can unsupervisedly generate interaction descriptors that make clusters corresponding to interaction types. And also we demonstrate that the model can infer possible hand-object interactions.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.