The Dual-Objective Triggers (DOT) is presented, the first transferable attack on OV-VIS that simultaneously exploits the vision–language coupling and temporal coherence, and Phase-Guided Ad-versarial Training is introduced, which injects perturbations primarily in the phase spectrum while blending amplitudes with clean references.
While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.g., zero-shot classification) and consequently lack generalizability across various multimodal tasks. To address this limitation, we propose a dual adversarial fine-tuning framework that jointly optimizes visual and semantic supervision signals from two modalities, enhancing model robustness while generalizing across multiple downstream tasks. The proposed framework comprises two core components, i.e., $\textbf{Visual}$ supervision branch and $\textbf{Semantic}$ supervision branch. The former branch leverages features from clean images, extracted via a frozen original vision encoder, to guide adversarial robustness while the latter incorporates caption-image alignment as a contextual signal to preserve semantic coherence under attack. Moreover, our method achieves cross-task robustness by simply replacing the CLIP vision encoder in the original model, with no need of separate task-specific retraining or architecture modifications.Extensive experiments demonstrate that our approach outperforms the state-of-the-art method in adversarial robustness evaluation across zero-shot classification, image captioning, and visual question answering (VQA) tasks.
Sibo Wang, Jie Zhang, Shiguang Shan et al.· 0 citations
Video Virtual Try-On (VVT) synthesizes a video of a person wearing a target garment while preserving identity, motion, and scene dynamics. Dominant approaches cast VVT as mask-conditioned video inpainting and rely on separate modules for human parsing, pose estimation, and garment warping. This multi-stage design complicates deployment and, more critically, allows errors in explicit geometric priors to propagate irreversibly into the generated video. We present UniVVT, a unified end-to-end framework that reframes VVT as semantically conditioned video generation, eliminating mask, pose, and warping modules at inference. At its core, a scene-task perceiver built on a Multimodal Large Language Model jointly encodes the source video, target garment, and task instruction into compact, task-aware latent tokens, implicitly capturing what to transfer and where and how to transfer it. A lightweight semantic bridge then aligns these tokens with the conditioning space of a diffusion-based video generator, enabling coherent garment transfer. To robustly couple the heterogeneous components, we devise a three-stage progressive training strategy comprising semantic alignment, joint task adaptation, and flexible-resolution refinement. Extensive experiments demonstrate that UniVVT achieves state-of-the-art performance across multiple benchmarks, validating implicit semantic guidance as a simple and effective alternative to fragile geometric preprocessing for end-to-end virtual try-on.
Yushe Cao, Shikun Feng, Fei Shen et al.· 0 citations
Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding. Existing explainability efforts rely on textual rationales or sparse bounding boxes, which struggle to capture complex video dynamics such as occlusions and non-rigid deformations. We propose Evidence-Backed Video Question Answering (E-VQA), a novel task requiring models to jointly output a semantic answer and precise spatio-temporal evidence: temporal segments and dense, tracked object segmentation masklets. To support this, we introduce ST-Evidence, the first human-verified benchmark for both discriminative and generative pixel-level grounding. Evaluations of state-of-the-art models reveal a critical decoupling between QA accuracy and true visual perception that scaling alone fails to bridge. To address this, we develop scalable, automated generation pipelines to create ST-Evidence-Instruct, a 160k-scale dataset bridging high-level reasoning with fine-grained grounding. Fine-tuning grounded Video LLMs on this data yields substantial gains over the corresponding size-matched UniPixel baselines (e.g., +27.2 t-mean and +13.8 J&F on a 7B model), establishing a robust baseline for explainable, evidence-backed video understanding. Code and data are available at https://github.com/SalesforceAIResearch/EVQA.
Shijie Wang, Honglu Zhou, Ziyang Wang et al.· 0 citations
This work proposes RITA, a Robust test-tIme prompt-TAdaptation framework that shifts from sample-level estimates to distribution-level alignment, and employs optimal transport to align the distribution of augmented visual features with textual prototypes, mitigating adversarial outliers and rectifying cross-modal semantic misalignment.
Xingyu Zhu, Huanshen Wu, Shuo Wang et al.· 1 citation
While generative models have become a standard approach for addressing the semantic-to-visual gap in Generalized Zero-Shot Learning (GZSL), existing architectures often struggle with two persistent limitations: cross-modal interference during condition fusion and severe overfitting to the visual distributions of seen classes. To address these bottlenecks, this paper introduces SemanticFlowNet, a framework based on Decoupled Semantic Flow Matching. Specifically, we propose a Decoupled Multi-modal Conditioning mechanism that relies on channel-wise concatenation of temporal encodings, semantic attributes, and visual contexts, which preserves the orthogonal subspaces of each modality and reduces interference. Additionally, we integrate a Dropout-enhanced Adaptive Layer Normalization (AdaLN) module to perturb the rigid memorization of seen classes, utilizing stochastic dropout within the state evolution to simulate the distributional variance of unseen domains. Finally, a Time-Aware Dynamic Reconstruction Penalty is introduced to enforce progressively stricter semantic alignment as the generative ordinary differential equation (ODE) trajectory converges to the target manifold. Evaluations on the CUB, SUN, and AWA2 benchmarks demonstrate the effectiveness of the proposed framework. Notably, SemanticFlowNet achieves a harmonic mean of 77.90% on the CUB dataset in the single-seed full-model setting, providing a competitive baseline for generative GZSL applications.
Chuyang Song, Mingyi Song, Yang Liu et al.· Electronics· 0 citations
This paper identifies three previously overlooked issues caused by inappropriate cross-modal interactions and excessive operations in the Simple Vision-Language Attack (SimVLA) pipeline, and proposes the SimVLA, which observably improves transferability and efficiency.
Yuchen Ren, Zhengyu Zhao, Chenhao Lin et al.· IEEE Transactions on Informa...· 0 citations