相关论文: Multimodal Knowledge Distillation for Egocentric A…

To reduce a model size but retain performance, we often rely on knowledge distillation (KD) which transfers knowledge from a large "teacher" model to a smaller "student" model. However, KD on multimodal datasets such as vision-language…

In multimodal sentiment analysis, collecting text data is often more challenging than video or audio due to higher annotation costs and inconsistent automatic speech recognition (ASR) quality. To address this challenge, our study has…

Diverse input data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while a (training) dataset could be accurately designed to include a variety of…

We propose a technique that tackles action detection in multimodal videos under a realistic and challenging condition in which only limited training data and partially observed modalities are available. Common methods in transfer learning…

Existing methods for distillation do not efficiently utilize the training data. This work presents a novel approach to perform distillation using only a subset of the training data, making it more data-efficient. For this purpose, the…

Vision-based policies are widely applied in robotics for tasks such as manipulation and locomotion. On lightweight mobile robots, however, they face a trilemma of limited scene transferability, restricted onboard computation resources, and…

Knowledge distillation is an effective method to transfer the knowledge from the cumbersome teacher model to the lightweight student model. Online knowledge distillation uses the ensembled prediction results of multiple student models as…

In this paper, we study a novel problem in egocentric action recognition, which we term as "Multimodal Generalization" (MMG). MMG aims to study how systems can generalize when data from certain modalities is limited or even completely…

Standard multi-modal models assume the use of the same modalities in training and inference stages. However, in practice, the environment in which multi-modal models operate may not satisfy such assumption. As such, their performances…

In 3D action recognition, there exists rich complementary information between skeleton modalities. Nevertheless, how to model and utilize this information remains a challenging problem for self-supervised 3D action representation learning.…

Human capability to anticipate near future from visual observations and non-verbal cues is essential for developing intelligent systems that need to interact with people. Several research areas, such as human-robot interaction (HRI),…

Depth perception is crucial for a wide range of robotic applications. Multi-frame self-supervised depth estimation methods have gained research interest due to their ability to leverage large-scale, unlabeled real-world data. However, the…

Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. Most MSA efforts are based on the assumption of modality completeness. However, in real-world applications, some practical factors cause…

Knowledge distillation has become an important approach to obtain a compact yet effective model. To achieve this goal, a small student model is trained to exploit the knowledge of a large well-trained teacher model. However, due to the…

Accurate driving behavior recognition and reasoning are critical for autonomous driving video understanding. However, existing methods often tend to dig out the shallow causal, fail to address spurious correlations across modalities, and…

There is no doubt that advanced artificial intelligence models and high quality data are the keys to success in developing computational pathology tools. Although the overall volume of pathology data keeps increasing, a lack of quality data…

Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data…

Dark videos often lose essential information, which causes the knowledge learned by networks is not enough to accurately recognize actions. Existing knowledge assembling methods require massive GPU memory to distill the knowledge from…

Multimodal egocentric activity recognition integrates visual and inertial cues for robust first-person behavior understanding. However, deploying such systems in open-world environments requires detecting novel activities while continuously…

We address a novel cross-domain few-shot learning task (CD-FSL) with multimodal input and unlabeled target data for egocentric action recognition. This paper simultaneously tackles two critical challenges associated with egocentric action…