Related papers: Students taught by multimodal teachers are superio…
In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…
Knowledge distillation is an effective approach to learn compact models (students) with the supervision of large and strong models (teachers). As empirically there exists a strong correlation between the performance of teacher and student…
Analyzing instructional interactions between an instructor and a learner who are co-present in the same physical space is a critical problem for educational support and skill transfer. Yet such face-to-face instructional scenes have not…
Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder efficient deployment. Knowledge distillation (KD) has emerged as a powerful approach for building…
A crucial component of an autonomous vehicle (AV) is the artificial intelligence (AI) is able to drive towards a desired destination. Today, there are different paradigms addressing the development of AI drivers. On the one hand, we find…
Robust perception at night remains challenging for thermal-infrared detection: low contrast and weak high-frequency cues lead to duplicate, overlapping boxes, missed small objects, and class confusion. Prior remedies either translate TIR to…
Our interaction with the world is an inherently multimodal experience. However, the understanding of human-to-object interactions has historically been addressed focusing on a single modality. In particular, a limited number of works have…
Robotic manipulation requires accurate perception of the environment, which poses a significant challenge due to its inherent complexity and constantly changing nature. In this context, RGB image and point-cloud observations are two…
Video representation learning is a vital problem for classification task. Recently, a promising unsupervised paradigm termed self-supervised learning has emerged, which explores inherent supervisory signals implied in massive data for…
Action recognition in dark or low-light (under-exposed) videos is a challenging task due to visibility degradation, which can hinder critical spatiotemporal details. This paper proposes ActLumos, a teacher-student framework that attains…
State-of-the-art object grasping methods rely on depth sensing to plan robust grasps, but commercially available depth sensors fail to detect transparent and specular objects. To improve grasping performance on such objects, we introduce a…
Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question…
In real-world scenarios, using multiple modalities like visible (RGB) and infrared (IR) can greatly improve the performance of a predictive task such as object detection (OD). Multimodal learning is a common way to leverage these…
Human action recognition in dark videos is a challenging task for computer vision. Recent research focuses on applying dark enhancement methods to improve the visibility of the video. However, such video processing results in the loss of…
In this study, we aim to predict the plausible future action steps given an observation of the past and study the task of instructional activity anticipation. Unlike previous anticipation tasks that aim at action label prediction, our work…
Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…
Most of existing video action recognition models ingest raw RGB frames. However, the raw video stream requires enormous storage and contains significant temporal redundancy. Video compression (e.g., H.264, MPEG-4) reduces superfluous…
Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object…
Continual learning focuses on incrementally training a model on a sequence of tasks with the aim of learning new tasks while minimizing performance drop on previous tasks. Existing approaches at the intersection of Continual Learning and…
This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is designed to leverage insights from both fine-grained and…