相关论文: FalconApp: Rapid iPhone Deployment of End-to-End P…

Perception-centric systems are typically implemented with a modular encoder-decoder pipeline: a vision backbone for feature extraction and a separate decoder (or late-fusion module) for task prediction. This raises a central question: is…

This paper introduces a holistic vision-language foundation model tailored for remote sensing, named Falcon. Falcon offers a unified, prompt-based paradigm that effectively executes comprehensive and complex remote sensing tasks. Falcon…

Human behaviors in the real world naturally encode rich, long-term contextual information that can be leveraged to train embodied agents for perception, understanding, and acting. However, existing capture systems typically rely on costly…

Active perception is a fundamental skill that enables us humans to deal with uncertainty in our inherently partially observable environment. For senses such as touch, where the information is sparse and local, active perception becomes…

The transfer of manipulation skills from human demonstration to robotic execution is often hindered by a "domain gap" in sensing and morphology. This paper introduces MagiClaw, a versatile two-finger end-effector designed to bridge this…

Deploying a humanoid robot to manipulate a new object has traditionally required one to two days of effort: data collection, manual annotation, 3D model acquisition, and model training. This paper presents an end-to-end rapid deployment…

Recent progress in imitation learning from human demonstrations has shown promising results in teaching robots manipulation skills. To further scale up training datasets, recent works start to use portable data collection devices without…

Facial landmark detection is a crucial prerequisite for many face analysis applications. Deep learning-based methods currently dominate the approach of addressing the facial landmark detection. However, such works generally introduce a…

Latest deep learning methods for object detection provide remarkable performance, but have limits when used in robotic applications. One of the most relevant issues is the long training time, which is due to the large size and imbalance of…

Autonomous vehicles demand high accuracy and robustness of perception algorithms. To develop efficient and scalable perception algorithms, the maximum information should be extracted from the available sensor data. In this work, we present…

Being accurate, efficient, and compact is essential to a facial landmark detector for practical use. To simultaneously consider the three concerns, this paper investigates a neat model with promising detection accuracy under wild…

Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon,…

Object pose estimation plays a vital role in mixed-reality interactions when users manipulate tangible objects as controllers. Traditional vision-based object pose estimation methods leverage 3D reconstruction to synthesize training data.…

The world is abundant with diverse materials, each possessing unique surface appearances that play a crucial role in our daily perception and understanding of their properties. Despite advancements in technology enabling the capture and…

We developed a robust solution for real-time 6D object detection in industrial applications by integrating FoundationPose, SAM2, and LightGlue, eliminating the need for retraining. Our approach addresses two key challenges: the requirement…

Facial attractiveness prediction (FAP) aims to assess facial attractiveness automatically based on human aesthetic perception. Previous methods using deep convolutional neural networks have improved the performance, but their large-scale…

Current autonomous driving systems are composed of a perception system and a decision system. Both of them are divided into multiple subsystems built up with lots of human heuristics. An end-to-end approach might clean up the system and…

As the quality of few shot facial animation from landmarks increases, new applications become possible, such as ultra low bandwidth video chat compression with a high degree of realism. However, there are some important challenges to tackle…

iPhone portrait-mode images contain a distinctive pattern in out-of-focus regions simulating the bokeh effect, which we term Apple's Synthetic Defocus Noise Pattern (SDNP). If overlooked, this pattern can interfere with blind forensic…

Efficient networks, e.g., MobileNetV2, EfficientNet, etc, achieves state-of-the-art (SOTA) accuracy with lightweight computation. However, existing homomorphic encryption (HE)-based two-party computation (2PC) frameworks are not optimized…