21 accepted papers
The advent of Vision-Language-Action (VLA) models represents a significant leap for embodied intelligence, yet their immense computational demands critically hinder deployment on resource-constrained robotic platforms. Intuitively, low-bit quantization is a prevalent and preferred technique for larg…
In recent years, the development of burst imaging technology has improved the capture and processing capabilities of visual data, enabling a wide range of applications. However, the redundancy in burst images leads to the increased storage and transmission demands, as well as reduced efficiency of d
This paper studies the problem of Cooperative Localization (CL) for multi-robot systems in 3-D environments, where a group of mobile robots jointly localize themselves by using measurements from onboard sensors and shared information from other robots. To ensure the efficiency of information fusion
3DGS has shown outstanding performance in multi-view geometry, driving its adoption in visual SLAM. However, real-time semantic 3DGS mapping faces challenges. Current methods typically treat semantics as external priors, making it hard to integrate them into SLAM tracking or loop closure correction.…
Despite rapid advancements in text-to-image (T2I) models, their safety mechanisms are vulnerable to adversarial prompts, which maliciously generate unsafe images. Current red-teaming methods for proactively assessing such vulnerabilities usually require white-box access to T2I models, and rely on in…
The established redundancy in visual tokens within large vision–language models (LVLMs) allows for pruning to effectively reduce their substantial computational demands. Empirical evidence from previous works indicates that visual tokens in later decoder stages receive less attention than shallow la…
This paper is concerned with the motion control problem of an aerial manipulator that consists of a quadrotor base and a manipulator. We propose a novel control strategy that incorporates a simplified model considering the critical dynamics, and a linear-MPC-based trajectory converter to ensure prec
Recent advancements in 3DGS-based explicit mapping have significantly improved SLAM performance, achieving more realistic environment reconstruction and faster processing. However, issues such as data loss caused by unstable data transmission, textureless and repetitive-texture often occur in real-w
Brain-inspired spiking neural networks (SNNs) provide energy-efficient computation through event-driven processing. However, the shared weights across multiple timesteps lead to serious temporal feature redundancy, limiting both efficiency and performance. This issue is further aggravated when proce…
Image restoration tasks like deblurring, denoising, and dehazing usually need distinct models for each degradation type, restricting their generalization in real-world scenarios with mixed or unknown degradations. In this work, we propose Defusion, a novel all-in-one image restoration framework that…
The significant differences in the physical properties of air and water pose a substantial challenge for the development of hybrid aerial-aquatic vehicle (HAAV), which leading to increased prototype size, heavier thrusters, and reduced efficiency or under-actuation in one of the mediums. This letter
Recently, there has been a widespread proliferation of "expert" language models that are specialized to a specific task or domain through parameter-efficient fine-tuning. How can we recycle large collections of expert language models to improve zero-shot generalization to unseen tasks? In this work,…
Face forgery detection becomes increasingly crucial due to the serious security issues caused by face manipulation techniques. Recent studies in deepfake detection have yielded promising results when the training and testing face forgeries are from the same domain. However, the problem remains chall…
Video action recognition is faced with the challenges of both huge computation burden and performance requirements. Using compressed domain data, which saves much decoding computation, is a possible solution. Unfortunately, existing compressed-domain-based (CD) methods fail to obtain high performanc…
A challenging problem called Nasty Source Free Domain Adaptation (Nasty-SFDA) is proposed in this work, where only a nasty source model and unlabeled target samples are available for DA. Further, after DA, the target model is expected to be a nasty model. In order to deal with Nasty-SFDA, Nasty HypO…
Compared with image few-shot learning, most of the existing few-shot video classification methods perform worse on feature matching, because they fail to sufficiently exploit the temporal information and relation. Specifically, frames are usually evenly sampled, which may miss important frames. On t…
Filter pruning is a commonly used method for compressing Convolutional Neural Networks (ConvNets), due to its friendly hardware supporting and flexibility. However, existing methods mostly need a cumbersome procedure, which brings many extra hyper-parameters and training epochs. This is because only…
Recently, video streams have occupied a large proportion of Internet traffic, most of which contain human faces. Hence, it is necessary to predict saliency on multiple-face videos, which can provide attention cues for many content based applications. However, most of multiple-face prediction works o…
The key challenge of knowledge distillation is to extract general, moderate and sufficient knowledge from a teacher network to guide a student network. In this paper, a novel Instance Relationship Graph (IRG) is proposed for knowledge distillation. It models three kinds of knowledge, including insta…
Although the recent success of convolutional neural network (CNN) advances state-of-the-art saliency prediction in static images, few work has addressed the problem of predicting attention in videos. On the other hand, we find that the attention of different subjects consistently focuses on a single…