In human-robot interaction (HRI), the beginning of an interaction is often complex. Whether the robot should communicate with the human is dependent on several situational factors (e.g., the current human’s activity, urgency of the interaction, etc.). We test whether large language models (LLM) and vision language models (VLM) can provide solutions to this problem. We compare four different system-design patterns using LLMs and VLMs, and test on a test set containing 84 human-robot situations. The test set mixes several publicly available datasets and also includes situations where the appropriate action to take is open-ended. Our results using the GPT-4o and Phi-3 Vision model indicate that LLMs and VLMs are capable of handling interaction beginnings when the desired actions are clear. The design using direct image input scored an 89% accuracy on the test set. Of the designs using indirect input, a combined text about human activity and gaze performed best with a 90% accuracy. However, challenges remain in the open-ended situations where the model must choose the priority between the human and robot situation. The design using direct image input mostly prioritized the robot situation, whereas the design with best performance using indirect input mostly prioritized the human situation. Such one-sided behavior could be crucial for practical HRI applications.

Recent large language models (LLMs) are capable of planning robot actions. In this paper, we explore how LLMs can be used for planning actions with tasks involving situational human-robot interaction (HRI). A key problem of applying LLMs in situational HRI is balancing between "respecting the current human’s activity" and "prioritizing the robot’s task," as well as understanding the timing of when to use the LLM to generate an action plan. In this paper, we propose a necessary plan-and-act skill design to solve the above problems. We show that a critical factor for enabling a robot to switch between passive / active interaction behavior is to provide the LLM with an action text about the current robot’s action. We also show that a second-stage question to the LLM (about the next timing to call the LLM) is necessary for planning actions at an appropriate timing. The skill design is applied to an Engage skill and is tested on four distinct interaction scenarios. We show that by using the skill design, LLMs can be leveraged to easily scale to different HRI scenarios with a reasonable success rate reaching 90% on the test scenarios.

This paper addresses the generation of explanations with visual examples. Given an input sample, we build a system that not only classifies it to a specific category, but also outputs linguistic explanations and a set of visual examples that render the decision interpretable. Focusing especially on the complementarity of the multimodal information, i.e., linguistic and visual examples, we attempt to achieve it by maximizing the interaction information, which provides a natural definition of complementarity from an information theoretical viewpoint. We propose a novel framework to generate complemental explanations, on which the joint distribution of the variables to explain, and those to be explained is parameterized by three different neural networks: predictor, linguistic explainer, and example selector. Explanation models are trained collaboratively to maximize the interaction information to ensure the generated explanation are complemental to each other for the target. The results of experiments conducted on several datasets demonstrate the effectiveness of the proposed method.

This study addresses generating counterfactual explanations with multimodal information. Our goal is not only to classify a video into a specific category, but also to provide explanations on why it is not categorized to a specific class with combinations of visual-linguistic information. Requirements that the expected output should satisfy are referred to as counterfactuality in this paper: (1) Compatibility of visual-linguistic explanations, and (2) Positiveness/negativeness for the specific positive/negative class. Exploiting a spatio-temporal region (tube) and an attribute as visual and linguistic explanations respectively, the explanation model is trained to predict the counterfactuality for possible combinations of multimodal information in a post-hoc manner. The optimization problem, which appears during training/inference, can be efficiently solved by inserting a novel neural network layer, namely the maximum subpath layer. We demonstrated the effectiveness of this method by comparison with a baseline of the action recognition datasets extended for this task. Moreover, we provide information-theoretical insight into the proposed method.

This paper introduces a novel variant of video summarization, namely building a summary that depends on the particular aspect of a video the viewer focuses on. We refer to this as viewpoint. To infer what the desired viewpoint may be, we assume that several other videos are available, especially groups of videos, e.g., as folders on a person's phone or laptop. The semantic similarity between videos in a group vs. the dissimilarity between groups is used to produce viewpoint-specific summaries. For considering similarity as well as avoiding redundancy, output summary should be (A) diverse, (B) representative of videos in the same group, and (C) discriminative against videos in the different groups. To satisfy these requirements (A)-(C) simultaneously, we proposed a novel video summarization method from multiple groups of videos. Inspired by Fisher's discriminant criteria, it selects summary by optimizing the combination of three terms (a) inner-summary, (b) inner-group, and (c) between-group variances defined on the feature representation of summary, which can simply represent (A)-(C). Moreover, we developed a novel dataset to investigate how well the generated summary reflects the underlying viewpoint. Quantitative and qualitative experiments conducted on the dataset demonstrate the effectiveness of proposed method.

In this paper, we specifically examine the training of a multi-label classifier from data with incompletely assigned labels. This problem is fundamentally important in many multi-label applications because it is almost impossible for human annotators to assign a complete set of labels, although their judgments are reliable. In other words, a multilabel dataset usually has properties by which (1) assigned labels are definitely positive and (2) some labels are absent but are still considered positive. Such a setting has been studied as a positive and unlabeled (PU) classification problem in a binary setting. We treat incomplete label assignment problems as a multi-label PU ranking, which is an extension of classical binary PU problems to the wellstudied rank-based multi-label classification. We derive the conditions that should be satisfied to cancel the negative effects of label incompleteness. Our experimentally obtained results demonstrate the effectiveness of these conditions.

We present a novel dataset and a novel algorithm for recognizing activities of daily living (ADL) from a first-person wearable camera. Handled objects are crucially important for egocentric ADL recognition. For specific examination of objects related to users' actions separately from other objects in an environment, many previous works have addressed the detection of handled objects in images captured from head-mounted and chest-mounted cameras. Nevertheless, detecting handled objects is not always easy because they tend to appear small in images. They can be occluded by a user's body. As described herein, we mount a camera on a user's wrist. A wrist-mounted camera can capture handled objects at a large scale, and thus it enables us to skip the object detection process. To compare a wrist-mounted camera and a head-mounted camera, we also developed a novel and publicly available dataset1that includes videos and annotations of daily activities captured simultaneously by both cameras. Additionally, we propose a discriminative video representation that retains spatial and temporal information after encoding the frame descriptors extracted by convolutional neural networks (CNN).

In this paper, we focus on training a classifier from large-scale data with incompletely assigned labels. In other words, we treat samples with following properties: 1. assigned labels are definitely positive, 2. absent labels are not necessarily negative, and 3. samples are allowed to take more than one label. These properties are frequently found in various kinds of computer vision tasks, including image and video classification and retrieval. Many online algorithms for multi-label task employ label sampling, which selects a label pair that reduces the largest penalty to update the model, thereby avoiding waste of computation. In the setting above, however, there are “false-negative” labels, which are originally positive labels but regarded as negative. Since it is high likely for label sampling to select these labels as negative labels in the sampled pair, it may severely degrade classification performance. In order to solve this problem while preserving convergence property of the online algorithms, we propose a novel label sampling approach, which aims to fetch “true-negative” labels via false-negativeness measure based on independently trained uni-class classifiers. Experimental results show the effectiveness of our approach.