Latest Articles for Human-Computer Interaction

STAformer enhances action prediction in videos through attention-based techniques.

Assessing how models perform in real-world task planning using a new framework.

A challenge to enhance robots' understanding of human interactions.

V-VIPE enhances 3D pose estimation from 2D images, overcoming angle challenges.

Research shows VLMs have poor accuracy in simple visual tasks compared to humans.

This study examines avatar interaction methods to improve VR experiences.

A voice-driven model transforming audio interaction with technology.

A new method helps robots learn by observing human interactions.

A new method enhances image retrieval by integrating human corrections into AI systems.

A study on enhancing AI's ability to follow natural language instructions.

Study reveals difficulties for humans and AI in recognizing each other.

Study evaluates sound design for remote robot operation in dangerous environments.

A new approach improves feedback collection for language models, saving time and costs.

A new dataset enhances machine speech for Mandarin, aiming for natural expression.

Researchers develop methods to better align language models with human preferences.

Analyzing how LLMs manage text inaccuracies in real-world scenarios.

New model improves action retrieval from images using person, objects, and context.

Effective communication is key for robots to follow human instructions accurately.

Researchers create a webcam-based dataset for pupil size measurement.

Examining the role of LLMs in qualitative analysis and human oversight.

A study on collecting and using user feedback to improve language models.

An overview of NLG progress, challenges, and future research directions.

New methods improve machine understanding of human emotions in speech.

A look into how generative IR systems can transform information seeking.

Length-Aware Latent Diffusion creates diverse human motions based on textual descriptions.

A method that combines visual and IMU data for better action recognition.

Research aims to develop language models with unique personalities for better human-like interactions.

A novel approach to improve language models using human feedback.

Examining the difficulties of creating effective reward functions in reinforcement learning.

Phi-3 models focus on safety and aligning with human values.

A new approach enhances SER systems by using noise environment descriptions.

New tests show AI struggles with changing game rules creatively.

New methods enhance action recognition in visual data with skeleton analysis.

A novel approach to predict how people visually search for objects.

A new framework improves connection between faces and voices, especially in noisy settings.

Examining the rise of few-shot action recognition in video analysis.

Research reveals how friendly prompts can mislead AI systems.

Introducing ESCAPE, a framework enhancing 3D human pose accuracy and speed.

This study evaluates CNN and Modified VGG16 models on emotion recognition tasks.

An overview of reinforcement learning challenges tied to reward errors.