Related papers: Towards Context-aware Interaction Recognition

Which object detector is suitable for your context sensitive task? Deep object detectors exploit scene context for recognition differently. In this paper, we group object detectors into 3 categories in terms of context use: no context by…

The number of categories for action recognition is growing rapidly. It is thus becoming increasingly hard to collect sufficient training data to learn conventional models for each category. This issue may be ameliorated by the increasingly…

We introduce context-aware translation, a novel method that combines the benefits of inpainting and image-to-image translation, respecting simultaneously the original input and contextual relevance -- where existing methods fall short. By…

Interactive Machine Learning (IML) shall enable intelligent systems to interactively learn from their end-users, and is quickly becoming more and more important. Although it puts the human in the loop, interactions are mostly performed via…

This paper presents Affecta-context, a general framework to facilitate behavior adaptation for social robots. The framework uses information about the physical context to guide its behaviors in human-robot interactions. It consists of two…

Socio-demographic user profiles are currently regarded as the most convenient base for successful personalized advertising. However, signs point to the dormant power of context recognition. While technologies that can sense the environment…

Recent approaches in robotics follow the insight that perception is facilitated by interaction with the environment. These approaches are subsumed under the term of Interactive Perception (IP). It provides the following benefits: (i)…

Change Captioning is a task that aims to describe the difference between images with natural language. Most existing methods treat this problem as a difference judgment without the existence of distractors, such as viewpoint changes.…

We propose a novel framework for video understanding, called Temporally Contextualized CLIP (TC-CLIP), which leverages essential temporal information through global interactions in a spatio-temporal domain within a video. To be specific, we…

The visual world around us can be described as a structured set of objects and their associated relations. An image of a room may be conjured given only the description of the underlying objects and their associated relations. While there…

Road detection is a fundamental task in autonomous navigation systems. In this paper, we consider the case of monocular road detection, where images are segmented into road and non-road regions. Our starting point is the well-known machine…

We address the problem of inferring self-supervised dense semantic correspondences between objects in multi-object scenes. The method introduces learning of class-aware dense object descriptors by providing either unsupervised discrete…

Anomaly detection usually assumes that abnormality is an intrinsic property of an observation. A defect is a defect, and a rare object is rare, regardless of where it appears. Many real-world anomalies do not work this way. A runner on a…

We investigate a human-like interpretable model of video understanding. Humans recognise complex activities in video by recognising critical spatio-temporal relations among explicitly recognised objects and parts, for example, an object…

The dominant paradigm in spatiotemporal action detection is to classify actions using spatiotemporal features learned by 2D or 3D Convolutional Networks. We argue that several actions are characterized by their context, such as relevant…

We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…

The interaction context (or environment) is key to any HCI task and especially to adaptive user interfaces (AUIs), since it represents the conditions under which users interact with computers. Unfortunately, there are currently no formal…

Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

Relationships among objects play a crucial role in image understanding. Despite the great success of deep learning techniques in recognizing individual objects, reasoning about the relationships among objects remains a challenging task.…

Establishing semantic correspondence is a core problem in computer vision and remains challenging due to large intra-class variations and lack of annotated data. In this paper, we aim to incorporate global semantic context in a flexible…