ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features

Extensive research has revealed that adversarial examples (AE) pose a significant threat to voice-controllable smart devices. Recent studies have proposed black-box adversarial attacks that require only the final transcription from an automatic speech recognition (ASR) system. However, these attacks typically involve many queries to the ASR, resulting in substantial costs. Moreover, AE-based adversarial audio samples are susceptible to ASR updates. In this paper, we identify the root cause of these limitations, namely the inability to construct AE attack samples directly around the decision boundary of deep learning (DL) models. Building on this observation, we propose ALIF, the first black-box adversarial linguistic feature-based attack pipeline. We leverage the reciprocal process of text-to-speech (TTS) and ASR models to generate perturbations in the linguistic embedding space where the decision boundary resides. Based on the ALIF pipeline, we present the ALIF-OTL and ALIF-OTA schemes for launching attacks in both the digital domain and the physical playback environment on four commercial ASRs and voice assistants. Extensive evaluations demonstrate that ALIF-OTL and -OTA significantly improve query efficiency by 97.7% and 73.3%, respectively, while achieving competitive performance compared to existing methods. Notably, ALIF-OTL can generate an attack sample with only one query. Furthermore, our test-of-time experiment validates the robustness of our approach against ASR updates.

Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions

Video recognition remains an open challenge, requiring the identification of diverse content categories within videos. Mainstream approaches often perform flat classification, overlooking the intrinsic hierarchical structure relating categories. To address this, we formalize the novel task of hierarchical video recognition, and propose a video-language learning framework tailored for hierarchical recognition. Specifically, our framework encodes dependencies between hierarchical category levels, and applies a top-down constraint to filter recognition predictions. We further construct a new fine-grained dataset based on medical assessments for rehabilitation of stroke patients, serving as a challenging benchmark for hierarchical recognition. Through extensive experiments, we demonstrate the efficacy of our approach for hierarchical recognition, significantly outperforming conventional methods, especially for fine-grained subcategories. The proposed framework paves the way for hierarchical modeling in video understanding tasks, moving beyond flat categorization.

MOSS: Motion-based 3D Clothed Human Synthesis from Monocular Video

Single-view clothed human reconstruction holds a central position in virtual reality applications, especially in contexts involving intricate human motions. It presents notable challenges in achieving realistic clothing deformation. Current methodologies often overlook the influence of motion on surface deformation, resulting in surfaces lacking the constraints imposed by global motion. To overcome these limitations, we introduce an innovative framework, Motion-Based 3D Clothed Humans Synthesis (MOSS), which employs kinematic information to achieve motion-aware Gaussian split on the human surface. Our framework consists of two modules: Kinematic Gaussian Locating Splatting (KGAS) and Surface Deformation Detector (UID). KGAS incorporates matrix-Fisher distribution to propagate global motion across the body surface. The density and rotation factors of this distribution explicitly control the Gaussians, thereby enhancing the realism of the reconstructed surface. Additionally, to address local occlusions in single-view, based on KGAS, UID identifies significant surfaces, and geometric reconstruction is performed to compensate for these deformations. Experimental results demonstrate that MOSS achieves state-of-the-art visual quality in 3D clothed human synthesis from monocular videos. Notably, we improve the Human NeRF and the Gaussian Splatting by 33.94% and 16.75% in LPIPS* respectively. Codes are available at https://wanghongsheng01.github.io/MOSS/.

NOVA-3D: Non-overlapped Views for 3D Anime Character Reconstruction

In the animation industry, 3D modelers typically rely on front and back non-overlapped concept designs to guide the 3D modeling of anime characters. However, there is currently a lack of automated approaches for generating anime characters directly from these 2D designs. In light of this, we explore a novel task of reconstructing anime characters from non-overlapped views. This presents two main challenges: existing multi-view approaches cannot be directly applied due to the absence of overlapping regions, and there is a scarcity of full-body anime character data and standard benchmarks. To bridge the gap, we present Non-Overlapped Views for 3D \textbf{A}nime Character Reconstruction (NOVA-3D), a new framework that implements a method for view-aware feature fusion to learn 3D-consistent features effectively and synthesizes full-body anime characters from non-overlapped front and back views directly. To facilitate this line of research, we collected the NOVA-Human dataset, which comprises multi-view images and accurate camera parameters for 3D anime characters. Extensive experiments demonstrate that the proposed method outperforms baseline approaches, achieving superior reconstruction of anime characters with exceptional detail fidelity. In addition, to further verify the effectiveness of our method, we applied it to the animation head reconstruction task and improved the state-of-the-art baseline to 94.453 in SSIM, 7.726 in LPIPS, and 19.575 in PSNR on average. Codes and datasets are available at https://wanghongsheng01.github.io/NOVA-3D/.

Gaussian Control with Hierarchical Semantic Graphs in 3D Human Recovery

Although 3D Gaussian Splatting (3DGS) has recently made progress in 3D human reconstruction, it primarily relies on 2D pixel-level supervision, overlooking the geometric complexity and topological relationships of different body parts. To address this gap, we introduce the Hierarchical Graph Human Gaussian Control (HUGS) framework for achieving high-fidelity 3D human reconstruction. Our approach involves leveraging explicitly semantic priors of body parts to ensure the consistency of geometric topology, thereby enabling the capture of the complex geometrical and topological associations among body parts. Additionally, we disentangle high-frequency features from global human features to refine surface details in body parts. Extensive experiments demonstrate that our method exhibits superior performance in human body reconstruction, particularly in enhancing surface details and accurately reconstructing body part junctions. Codes are available at https://wanghongsheng01.github.io/HUGS/.

NieR: Normal-Based Lighting Scene Rendering

In real-world road scenes, diverse material properties lead to complex light reflection phenomena, making accurate color reproduction crucial for enhancing the realism and safety of simulated driving environments. However, existing methods often struggle to capture the full spectrum of lighting effects, particularly in dynamic scenarios where viewpoint changes induce significant material color variations. To address this challenge, we introduce NieR (Normal-Based Lighting Scene Rendering), a novel framework that takes into account the nuances of light reflection on diverse material surfaces, leading to more precise rendering. To simulate the lighting synthesis process, we present the LD (Light Decomposition) module, which captures the lighting reflection characteristics on surfaces. Furthermore, to address dynamic lighting scenes, we propose the HNGD (Hierarchical Normal Gradient Densification) module to overcome the limitations of sparse Gaussian representation. Specifically, we dynamically adjust the Gaussian density based on normal gradients. Experimental evaluations demonstrate that our method outperforms state-of-the-art (SOTA) methods in terms of visual quality and exhibits significant advantages in performance indicators. Codes are available at https://wanghongsheng01.github.io/NieR/.

RemoCap: Disentangled Representation Learning for Motion Capture

Reconstructing 3D human bodies from realistic motion sequences remains a challenge due to pervasive and complex occlusions. Current methods struggle to capture the dynamics of occluded body parts, leading to model penetration and distorted motion. RemoCap leverages Spatial Disentanglement (SD) and Motion Disentanglement (MD) to overcome these limitations. SD addresses occlusion interference between the target human body and surrounding objects. It achieves this by disentangling target features along the dimension axis. By aligning features based on their spatial positions in each dimension, SD isolates the target object's response within a global window, enabling accurate capture despite occlusions. The MD module employs a channel-wise temporal shuffling strategy to simulate diverse scene dynamics. This process effectively disentangles motion features, allowing RemoCap to reconstruct occluded parts with greater fidelity. Furthermore, this paper introduces a sequence velocity loss that promotes temporal coherence. This loss constrains inter-frame velocity errors, ensuring the predicted motion exhibits realistic consistency. Extensive comparisons with state-of-the-art (SOTA) methods on benchmark datasets demonstrate RemoCap's superior performance in 3D human body reconstruction. On the 3DPW dataset, RemoCap surpasses all competitors, achieving the best results in MPVPE (81.9), MPJPE (72.7), and PA-MPJPE (44.1) metrics. Codes are available at https://wanghongsheng01.github.io/RemoCap/.

When LLM-based Code Generation Meets the Software Development Process

Software process models play a pivotal role in fostering collaboration and communication within software teams, enabling them to tackle intricate development tasks effectively. This paper introduces LCG, a code generation framework inspired by established software engineering practices. LCG leverages multiple Large Language Model (LLM) agents to emulate various software process models, namely LCGWaterfall, LCGTDD, and LCGScrum. Each model assigns LLM agents specific roles such as requirement engineer, architect, developer, tester, and scrum master, mirroring typical development activities and communication patterns. Through collaborative efforts utilizing chain-of-thought and prompt composition techniques, the agents continuously refine themselves to enhance code quality. Utilizing GPT3.5 as the underlying LLM and baseline (GPT), we evaluate LCG across four code generation benchmarks: HumanEval, HumanEval-ET, MBPP, and MBPP-ET. Results indicate LCGScrum outperforms other models, achieving Pass@1 scores of 75.2, 65.5, 82.5, and 56.7 in HumanEval, HumanEval-ET, MBPP, and MBPP-ET, respectively - an average 15% improvement over GPT. Analysis reveals distinct impacts of development activities on generated code, with design and code reviews contributing to enhanced exception handling, while design, testing, and code reviews mitigate code smells. Furthermore, temperature values exhibit negligible influence on Pass@1 across all models. However, variations in Pass@1 are notable for different GPT3.5 model versions, ranging from 5 to over 60 in HumanEval, highlighting the stability of LCG across model versions. This stability underscores the importance of adopting software process models to bolster the quality and consistency of LLM-generated code.

Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection

Deepfake technology has given rise to a spectrum of novel and compelling applications. Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive confusion and deception, shattering our faith that seeing is believing. One aspect that has been overlooked so far is that current deepfake detection approaches may easily fall into the trap of overfitting, focusing only on forgery clues within one or a few local regions. Moreover, existing works heavily rely on neural networks to extract forgery features, lacking theoretical constraints guaranteeing that sufficient forgery clues are extracted and superfluous features are eliminated. These deficiencies culminate in unsatisfactory accuracy and limited generalizability in real-life scenarios. In this paper, we try to tackle these challenges through three designs: (1) We present a novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature. (2) Based on the information bottleneck theory, we derive Local Information Loss to guarantee the orthogonality of local representations while preserving comprehensive task-relevant information. (3) Further, to fuse the local representations and remove task-irrelevant information, we arrive at a Global Information Loss through the theoretical analysis of mutual information. Empirically, our method achieves state-of-the-art performance on five benchmark datasets.Our code is available at \url{https://github.com/QingyuLiu/Exposing-the-Deception}, hoping to inspire researchers.

CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge

Most of existing category-level object pose estimation methods devote to learning the object category information from point cloud modality. However, the scale of 3D datasets is limited due to the high cost of 3D data collection and annotation. Consequently, the category features extracted from these limited point cloud samples may not be comprehensive. This motivates us to investigate whether we can draw on knowledge of other modalities to obtain category information. Inspired by this motivation, we propose CLIPose, a novel 6D pose framework that employs the pre-trained vision-language model to develop better learning of object category information, which can fully leverage abundant semantic knowledge in image and text modalities. To make the 3D encoder learn category-specific features more efficiently, we align representations of three modalities in feature space via multi-modal contrastive learning. In addition to exploiting the pre-trained knowledge of the CLIP's model, we also expect it to be more sensitive with pose parameters. Therefore, we introduce a prompt tuning approach to fine-tune image encoder while we incorporate rotations and translations information in the text descriptions. CLIPose achieves state-of-the-art performance on two mainstream benchmark datasets, REAL275 and CAMERA25, and runs in real-time during inference (40FPS).