Related papers: Learning from Observer Gaze:Zero-Shot Attention Pr…
Visual Question Answering (VQA) presents a unique challenge by requiring models to understand and reason about visual content to answer questions accurately. Existing VQA models often struggle with biases introduced by the training data,…
Human-Object Interaction (HOI) detection devotes to learn how humans interact with surrounding objects via inferring triplets of < human, verb, object >. However, recent HOI detection methods mostly rely on additional annotations (e.g.,…
Most existing Human-Object Interaction~(HOI) Detection methods rely heavily on full annotations with predefined HOI categories, which is limited in diversity and costly to scale further. We aim at advancing zero-shot HOI detection to detect…
Human-Object Interaction (HOI) detection is a longstanding computer vision problem concerned with predicting the interaction between humans and objects. Current HOI models rely on a vocabulary of interactions at training and inference time,…
Driver visual attention prediction is a critical task in autonomous driving and human-computer interaction (HCI) research. Most prior studies focus on estimating attention allocation at a single moment in time, typically using static RGB…
The advent of industrial robotics and autonomous systems endow human-robot collaboration in a massive scale. However, current industrial robots are restrained in co-working with human in close proximity due to inability of interpreting…
Spatio-temporal Human-Object Interaction (ST-HOI) detection aims at detecting HOIs from videos, which is crucial for activity understanding. In daily HOIs, humans often interact with a variety of objects, e.g., holding and touching dozens…
Human-object interaction (HOI) detection aims to detect interactions between humans and objects in images. While recent advances have improved performance on existing benchmarks, their evaluations mainly focus on overall prediction accuracy…
It is well known that human gaze carries significant information about visual attention. However, there are three main difficulties in incorporating the gaze data in an attention mechanism of deep neural networks: 1) the gaze fixation…
Eye-tracking has potential to provide rich behavioral data about human cognition in ecologically valid environments. However, analyzing this rich data is often challenging. Most automated analyses are specific to simplistic artificial…
Understanding what makes a video memorable has important applications in advertising or education technology. Towards this goal, we investigate spatio-temporal attention mechanisms underlying video memorability. Different from previous…
Zero-Input AI (ZIA) introduces a novel framework for human-computer interaction by enabling proactive intent prediction without explicit user commands. It integrates gaze tracking, bio-signals (EEG, heart rate), and contextual data (time,…
Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen categories, showing impressive results on various zero-shot…
Human-object interaction (HOI) detection aims to comprehend the intricate relationships between humans and objects, predicting $<human, action, object>$ triplets, and serving as the foundation for numerous computer vision tasks. The…
Human-object interaction (HOI) synthesis is important for various applications, ranging from virtual reality to robotics. However, acquiring 3D HOI data is challenging due to its complexity and high cost, limiting existing methods to the…
Human-Object Interaction (HOI) detection aims to localize human-object pairs and comprehend their interactions. Recently, two-stage transformer-based methods have demonstrated competitive performance. However, these methods frequently focus…
Human-object interaction (HOI) detection aims to localize human-object pairs and the interactions between them. Existing methods operate under a closed-world assumption, treating the task as a classification problem over a small, predefined…
Text-conditioned human motion generation has experienced significant advancements with diffusion models trained on extensive motion capture data and corresponding textual annotations. However, extending such success to 3D dynamic…
Modern human-object interaction (HOI) detection approaches can be divided into one-stage methods and twostage ones. One-stage models are more efficient due to their straightforward architectures, but the two-stage models are still…
A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution. The lack of positive labels can lead to…