Related papers: Learning Skill-Attributes for Transferable Assessm…
Gauging an individual's skill level is crucial, as it inherently shapes their behavior. Quantifying skill, however, is challenging because it is latent to the observed actions. To explore skill understanding in human behavior, we focus on…
Job transitions and upskilling are common actions taken by many industry working professionals throughout their career. With the current rapidly changing job landscape where requirements are constantly changing and industry sectors are…
Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and…
Key challenges for the deployment of reinforcement learning (RL) agents in the real world are the discovery, representation and reuse of skills in the absence of a reward function. To this end, we propose a novel approach to learn a…
Recent studies have made notable progress in video representation learning by transferring image-pretrained models to video tasks, typically with complex temporal modules and video fine-tuning. However, fine-tuning heavy modules may…
Equipping Large Language Model (LLM) agents with domain-specific skills is critical for tackling complex tasks. Yet, manual authoring creates a severe scalability bottleneck. Conversely, automated skill generation often yields fragile or…
Video generation has achieved remarkable progress with the introduction of diffusion models, which have significantly improved the quality of generated videos. However, recent research has primarily focused on scaling up model training,…
With advances in optical sensor technology, heterogeneous camera systems are increasingly used for high-resolution (HR) video acquisition and analysis. However, motion transfer across multiple cameras poses challenges. To address this, we…
Object handover is a common form of interaction that is widely present in collaborative tasks. However, achieving it efficiently remains a challenge. We address the problem of ensuring resilient robotic actions that can adapt to complex…
We propose a multiple instance learning approach to content-based retrieval of classroom video for the purpose of supporting human assessing the learning environment. The key element of our approach is a mapping between the semantic…
We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that…
Utilizing large pre-trained models for specific tasks has yielded impressive results. However, fully fine-tuning these increasingly large models is becoming prohibitively resource-intensive. This has led to a focus on more…
Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks. An important question is to determine task transferability, i.e. given a common…
Spatio-temporal action detection is an important and challenging problem in video understanding. The existing action detection benchmarks are limited in aspects of small numbers of instances in a trimmed video or low-level atomic actions.…
Although language models are trained to mimic humans, the resulting systems display capabilities beyond the scope of any one person. To understand this phenomenon, we use a controlled setting to identify properties of the training data that…
Recent advancements in whole-body control through deep reinforcement learning have enabled humanoid robots to achieve remarkable progress in real-world chal lenging locomotion skills. However, existing approaches often struggle with…
Objective technical skill assessment is crucial for effective training of new surgeons in robot-assisted surgery. With advancements in surgical training programs in both physical and virtual environments, it is imperative to develop…
Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…
Sports video understanding requires perceiving high-speed dynamics, complex rules, and long temporal contexts. Yet, current Multimodal Large Language Models (MLLMs) remain narrowly focused on single sports, specific tasks, or training-free…
The availability of abundant labeled data in recent years led the researchers to introduce a methodology called transfer learning, which utilizes existing data in situations where there are difficulties in collecting new annotated data.…