29 accepted papers
With the rapid advancement of high-fidelity video generation models, robust AI-generated video (AIGV) detection has become increasingly needed. While most AIGV detection methods operate in the decoded pixel domain, we observe that detection in the pixel domain inevitably entangles task-irrelevant se…
Large Vision-Language Models excel at multimodal understanding but struggle to deeply integrate visual information into their predominantly text-based reasoning processes, a key challenge in mirroring human cognition. To address this, we introduce DeepEyes, a model that learns to ``think with images…
In the field of Compressive Sensing (CS), deep unrolling networks (DUNs) have demonstrated exceptional performance and interpretability by integrating traditional optimization solvers with deep networks. However, existing DUNs suffer from homogenization in cross-stage feature extraction and insuffic
Mobile motion sensors such as accelerometers and gyroscopes are now ubiquitously accessible by third-party apps via standard APIs. While enabling rich functionalities like activity recognition and step counting, this openness has also enabled unregulated inference of sensitive user traits, such as g
We study the best arm identification (BAI) problem with potentially biased offline data in the fixed confidence setting, which commonly arises in real-world scenarios such as clinical trials. We prove an impossibility result for adaptive algorithms without prior knowledge of the bias bound between o
The evolution of video generation techniques, such as Sora, has made it increasingly easy to produce high-fidelity AI-generated videos, raising public concern over the dissemination of synthetic content. However, existing detection methodologies remain limited by their insufficient exploration of te…
Gas source localization in complex environments is critical for applications such as environmental monitoring, industrial safety, and disaster response. Traditional methods often struggle with the challenges posed by a lack of environmental topography integration, especially when interactions betwee
The conversion of monocular RGB images to depth maps is crucial in robotic applications. Current supervised learning approaches, dependent on high-quality RGB-Depth pairs, struggle with indoor environments characterized by multiple objects and fluctuating lighting, leading to inaccurate and unstable…
Most existing 3D Gaussian Splatting (3DGS) compression schemes focus on producing compact 3DGS representation via implicit data embedding. They have long encoding and decoding times and highly customized data format, making it difficult for widespread deployment. This paper presents a new 3DGS compr…
Large Language Models (LLMs) demonstrate impressive zero-shot performance across a wide range of natural language processing tasks. Integrating various modality encoders further expands their capabilities, giving rise to Multimodal Large Language Models (MLLMs) that process not only text but also vi…
The prevalence of depression is escalating, especially among youth, which has become a critical mental health concern. Current assessment methods, relying heavily on questionnaires, clinical observations, and AI-driven analyses, are limited by their focus on single-event data, failing to encapsulate…
Recent studies have shown that large vision-language models (LVLMs) often suffer from the issue of object hallucinations (OH). To mitigate this issue, we introduce an efficient method that edits the model weights based on an unsafe subspace, which we call HalluSpace in this paper. With truthful and…
The current face recognition (FR) algorithms has achieved a high level of accuracy, making further improvements increasingly challenging. While existing FR algorithms primarily focus on optimizing margins and loss functions, limited attention has been given to exploring the feature representation sp…
"Generic event boundary detection (GEBD) aims at pinpointing event boundaries naturally perceived by humans, playing a crucial role in understanding long-form videos. Given the diverse nature of generic boundaries, spanning different video appearances, objects, and actions, this task remains challen…
"Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language. However, typographic attacks, which disrupt Vision-Language Models (VLMs) such as Contrastive Lang…
The knowledge gradient (KG) algorithm is a popular policy for the best arm identification (BAI) problem. It is built on the simple idea of always choosing the measurement that yields the greatest expected one-step improvement in the estimate of the best mean of the arms. In this research, we show th…
In this paper, we propose an improved distributed fusion algorithm under the Labeled multi-Bernoulli (LMB) filter framework. Firstly, the LMB parameter set is augmented by a new group variable, which is able to record the matching information of the neighbour sensors. Then the matching LMB component…
Spoken language understanding (SLU), one of the key enabling technologies for human-computer interaction in IoT devices, provides an easy-to-use user interface. Human speech can contain a lot of user-sensitive information, such as gender, identity, and sensitive content. New types of security and pr…
Online action detection has attracted increasing research interests in recent years. Current works model historical dependencies and anticipate the future to perceive the action evolution within a video segment and improve the detection accuracy. However, the existing paradigm ignores category-level…
Some applications may require performing face recognition (FR) on third-party servers, which could be accessed by attackers with malicious intents to compromise the privacy of users’ face information. This paper advocates a practical privacy-preserving FR scheme without key management realized in…
Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency. The recent proposed CondenseNet has shown that this mechanism can be further improved if redundant features are removed. In this paper, we propose an alternative approach named…
This paper presents an enhanced two-step method for tracking an indoor point target using the time difference of arrival (TDOA) measurements from an ultra wideband (UWB) positioning system. Again, the algorithm preprocesses the raw TDOAs and then feeds the results to a recursively bounded grid-based…
Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E) training of deep networks usually suffers from high GPUs memory footprint. This paper aims to address this problem by revisiting the locally supervised learning, where a network is split into gradient-isolat…
The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and high memory footprint. Inspired by the fact that not all regions in an image are task-relevant, we propose a novel framewor…
Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks. Existing works mainly exploit architecture redundancy in network depth or width. In this paper, we focus on spatial redundancy of input samples and propose a novel Res…
This paper considers exploiting the time difference of arrival (TDOA) measurements from a ultra wideband (UWB) indoor positioning system to locate a moving point target. In indoor environments, measured TDOAs are subject to large errors due to multipath and/or non-line-of-sight (NLOS) propagation. B…
Video object segmentation is a fundamental yet challenging task in computer vision community. In this paper, we formulate this problem as a Markov Decision Process, where agents are learned to segment object regions under a deep reinforcement learning framework. Essentially, learning agents for segm…
Identifying the location of a target is a fundamental application in multistatic sonar. Numerous attempts have been made to improve the accuracy, computational efficiency and robustness of target positioning. Previous studies mostly use time delay and angle measurements for localization, or time del…
Object segmentation in weakly labelled videos is an interesting yet challenging task, which aims at learning to perform category-specific video object segmentation by only using video-level tags. Existing works in this research area might still have some limitations, e.g., lack of effective DNN-base…