Related papers: Beyond Sequences: A Benchmark for Atomic Hand-Obje…
Human-object interaction detection (HOID) refers to localizing interactive human-object pairs in images and identifying the interactions. Since there could be an exponential number of object-action combinations, labeled data is limited -…
Hand-object interaction detection remains an open challenge in real-time applications, where intuitive user experiences depend on fast and accurate detection of interactions with surrounding objects. We propose an efficient approach for…
In many real-world applications involving static environments, the spatial layout of objects remains consistent across instances. However, state-of-the-art object detection models often fail to leverage this spatial prior, resulting in…
Tasks related to human hands have long been part of the computer vision community. Hands being the primary actuators for humans, convey a lot about activities and intents, in addition to being an alternative form of…
Understanding a scene by decoding the visual relationships depicted in an image has been a long studied problem. While the recent advances in deep learning and the usage of deep neural networks have achieved near human accuracy on many…
Deep learning has achieved remarkable success in modeling sequential data, including event sequences, temporal point processes, and irregular time series. Recently, transformers have largely replaced recurrent networks in these tasks.…
Recent approaches have successfully focused on the segmentation of static reconstructions, thereby equipping downstream applications with semantic 3D understanding. However, the world in which we live is dynamic, characterized by numerous…
The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond. Typical approaches decouple this problem by first extracting local spatiotemporal…
The chronological order of user-item interactions can reveal time-evolving and sequential user behaviors in many recommender systems. The items that users will interact with may depend on the items accessed in the past. However, the…
Humans in contrast to robots are excellent in performing fine manipulation tasks owing to their remarkable dexterity and sensorimotor organization. Enabling robots to acquire such capabilities, necessitates a framework that not only…
Progress in embodied intelligence increasingly depends on scalable data infrastructure. While vision and language have scaled with internet corpora, learning physical interaction remains constrained by the lack of large, diverse, and richly…
In this work we formulate the problem of image captioning as a multimodal translation task. Analogous to machine translation, we present a sequence-to-sequence recurrent neural networks (RNN) model for image caption generation. Different…
Sketch is an important media for human to communicate ideas, which reflects the superiority of human intelligence. Studies on sketch can be roughly summarized into recognition and generation. Existing models on image recognition failed to…
Time-lapse image sequences offer visually compelling insights into dynamic processes that are too slow to observe in real time. However, playing a long time-lapse sequence back as a video often results in distracting flicker due to random…
With the availability of egocentric 3D hand-object interaction datasets, there is increasing interest in developing unified models for hand-object pose estimation and action recognition. However, existing methods still struggle to recognise…
Gesture recognition is a very essential technology for many wearable devices. While previous algorithms are mostly based on statistical methods including the hidden Markov model, we develop two dynamic hand gesture recognition techniques…
Human actions in video sequences are characterized by the complex interplay between spatial features and their temporal dynamics. In this paper, we propose novel tensor representations for compactly capturing such higher-order relationships…
Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences. To address this limitation, we express the…
Understanding human intentions during interactions has been a long-lasting theme, that has applications in human-robot interaction, virtual reality and surveillance. In this study, we focus on full-body human interactions with large-sized…
Edge computing allows more computing tasks to take place on the decentralized nodes at the edge of networks. Today many delay sensitive, mission-critical applications can leverage these edge devices to reduce the time delay or even to…