Yanbin Hao

Yanbin Hao, Shuo Wang, Pei Cao et al.

Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current research on video attention generally focuses on adopting a specific aspect of contexts (e.g., channel, spatial/temporal, or global context) to refine the features and neglects their underlying correlation when computing attentions. This leads to incomplete context utilization and hence bears the weakness of limited performance improvement. To tackle the problem, this paper proposes an efficient attention-in-attention (AIA) method for element-wise feature refinement, which investigates the feasibility of inserting the channel context into the spatio-temporal attention learning module, referred to as CinST, and also its reverse variant, referred to as STinC. Specifically, we instantiate the video feature contexts as dynamics aggregated along a specific axis with global average and max pooling operations. The workflow of an AIA module is that the first attention block uses one kind of context information to guide the gating weights calculation of the second attention that targets at the other context. Moreover, all the computational operations in attention units act on the pooled dimension, which results in quite few computational cost increase ($<$0.02\%). To verify our method, we densely integrate it into two classical video network backbones and conduct extensive experiments on several standard video classification benchmarks. The source code of our AIA is available at \url{https://github.com/haoyanbin918/Attention-in-Attention}.

Yanbin Hao, Hao Zhang, Chong-Wah Ngo et al.

Learning discriminative representation from the complex spatio-temporal dynamic space is essential for video recognition. On top of those stylized spatio-temporal computational units, further refining the learnt feature with axial contexts is demonstrated to be promising in achieving this goal. However, previous works generally focus on utilizing a single kind of contexts to calibrate entire feature channels and could hardly apply to deal with diverse video activities. The problem can be tackled by using pair-wise spatio-temporal attentions to recompute feature response with cross-axis contexts at the expense of heavy computations. In this paper, we propose an efficient feature refinement method that decomposes the feature channels into several groups and separately refines them with different axial contexts in parallel. We refer this lightweight feature calibration as group contextualization (GC). Specifically, we design a family of efficient element-wise calibrators, i.e., ECal-G/S/T/L, where their axial contexts are information dynamics aggregated from other axes either globally or locally, to contextualize feature channel groups. The GC module can be densely plugged into each residual layer of the off-the-shelf video networks. With little computational overhead, consistent improvement is observed when plugging in GC on different networks. By utilizing calibrators to embed feature with four different kinds of contexts in parallel, the learnt representation is expected to be more resilient to diverse types of activities. On videos with rich temporal variations, empirically GC can boost the performance of 2D-CNN (e.g., TSN and TSM) to a level comparable to the state-of-the-art video networks. Code is available at https://github.com/haoyanbin918/Group-Contextualization.

Jiarui Yu, Haoran Li, Yanbin Hao et al.

The large-scale visual-language pre-trained model, Contrastive Language-Image Pre-training (CLIP), has significantly improved image captioning for scenarios without human-annotated image-caption pairs. Recent advanced CLIP-based image captioning without human annotations follows a text-only training paradigm, i.e., reconstructing text from shared embedding space. Nevertheless, these approaches are limited by the training/inference gap or huge storage requirements for text embeddings. Given that it is trivial to obtain images in the real world, we propose CLIP-guided text GAN (CgT-GAN), which incorporates images into the training process to enable the model to "see" real visual modality. Particularly, we use adversarial training to teach CgT-GAN to mimic the phrases of an external text corpus and CLIP-based reward to provide semantic guidance. The caption generator is jointly rewarded based on the caption naturalness to human language calculated from the GAN's discriminator and the semantic guidance reward computed by the CLIP-based reward module. In addition to the cosine similarity as the semantic guidance reward (i.e., CLIP-cos), we further introduce a novel semantic guidance reward called CLIP-agg, which aligns the generated caption with a weighted text embedding by attentively aggregating the entire corpus. Experimental results on three subtasks (ZS-IC, In-UIC and Cross-UIC) show that CgT-GAN outperforms state-of-the-art methods significantly across all metrics. Code is available at https://github.com/Lihr747/CgtGAN.

Zhicai Wang, Yanbin Hao, Tingting Mu et al.

It is well-known that zero-shot learning (ZSL) can suffer severely from the problem of domain shift, where the true and learned data distributions for the unseen classes do not match. Although transductive ZSL (TZSL) attempts to improve this by allowing the use of unlabelled examples from the unseen classes, there is still a high level of distribution shift. We propose a novel TZSL model (named as Bi-VAEGAN), which largely improves the shift by a strengthened distribution alignment between the visual and auxiliary spaces. The key proposal of the model design includes (1) a bi-directional distribution alignment, (2) a simple but effective L_2-norm based feature normalization approach, and (3) a more sophisticated unseen class prior estimation approach. In benchmark evaluation using four datasets, Bi-VAEGAN achieves the new state of the arts under both the standard and generalized TZSL settings. Code could be found at https://github.com/Zhicaiwww/Bi-VAEGAN

Hao Zhang, Lechao Cheng, Yanbin Hao et al.

Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes $T$ times longer sequence than the latter under the current attention of quadratic complexity $(T^2N^2)$. The existing works treat the temporal axis as a simple extension of spatial axes, focusing on shortening the spatio-temporal sequence by either generic pooling or local windowing without utilizing temporal redundancy. However, videos naturally contain redundant information between neighboring frames; thereby, we could potentially suppress attention on visually similar frames in a dilated manner. Based on this hypothesis, we propose the LAPS, a long-term ``\textbf{\textit{Leap Attention}}'' (LA), short-term ``\textbf{\textit{Periodic Shift}}'' (\textit{P}-Shift) module for video transformers, with $(2TN^2)$ complexity. Specifically, the ``LA'' groups long-term frames into pairs, then refactors each discrete pair via attention. The ``\textit{P}-Shift'' exchanges features between temporal neighbors to confront the loss of short-term dynamics. By replacing a vanilla 2D attention with the LAPS, we could adapt a static transformer into a video one, with zero extra parameters and neglectable computation overhead ($\sim$2.6\%). Experiments on the standard Kinetics-400 benchmark demonstrate that our LAPS transformer could achieve competitive performances in terms of accuracy, FLOPs, and Params among CNN and transformer SOTAs. We open-source our project in \sloppy \href{https://github.com/VideoNetworks/LAPS-transformer}{\textit{\color{magenta}{https://github.com/VideoNetworks/LAPS-transformer}}} .

Zhicai Wang, Yanbin Hao, Xingyu Gao et al.

Vision multi-layer perceptrons (MLPs) have shown promising performance in computer vision tasks, and become the main competitor of CNNs and vision Transformers. They use token-mixing layers to capture cross-token interactions, as opposed to the multi-head self-attention mechanism used by Transformers. However, the heavily parameterized token-mixing layers naturally lack mechanisms to capture local information and multi-granular non-local relations, thus their discriminative power is restrained. To tackle this issue, we propose a new positional spacial gating unit (PoSGU). It exploits the attention formulations used in the classical relative positional encoding (RPE), to efficiently encode the cross-token relations for token mixing. It can successfully reduce the current quadratic parameter complexity $O(N^2)$ of vision MLPs to $O(N)$ and $O(1)$. We experiment with two RPE mechanisms, and further propose a group-wise extension to improve their expressive power with the accomplishment of multi-granular contexts. These then serve as the key building blocks of a new type of vision MLP, referred to as PosMLP. We evaluate the effectiveness of the proposed approach by conducting thorough experiments, demonstrating an improved or comparable performance with reduced parameter complexity. For instance, for a model trained on ImageNet1K, we achieve a performance improvement from 72.14\% to 74.02\% and a learnable parameter reduction from $19.4M$ to $18.2M$. Code could be found at https://github.com/Zhicaiwww/PosMLP.

Xingyu Zhu, Beier Zhu, Yi Tan et al.

Vision-language models such as CLIP are capable of mapping the different modality data into a unified feature space, enabling zero/few-shot inference by measuring the similarity of given images and texts. However, most existing methods overlook modality gaps in CLIP's encoded features, which is shown as the text and image features lie far apart from each other, resulting in limited classification performance. To tackle this issue, we introduce a method called Selective Vision-Language Subspace Projection (SSP), which incorporates local image features and utilizes them as a bridge to enhance the alignment between image-text pairs. Specifically, our SSP framework comprises two parallel modules: a vision projector and a language projector. Both projectors utilize local image features to span the respective subspaces for image and texts, thereby projecting the image and text features into their respective subspaces to achieve alignment. Moreover, our approach entails only training-free matrix calculations and can be seamlessly integrated into advanced CLIP-based few-shot learning frameworks. Extensive experiments on 11 datasets have demonstrated SSP's superior text-image alignment capabilities, outperforming the state-of-the-art alignment methods. The code is available at https://github.com/zhuhsingyuu/SSP

Ouxiang Li, Jiayin Cai, Yanbin Hao et al.

With recent generative models facilitating photo-realistic image synthesis, the proliferation of synthetic images has also engendered certain negative impacts on social platforms, thereby raising an urgent imperative to develop effective detectors. Current synthetic image detection (SID) pipelines are primarily dedicated to crafting universal artifact features, accompanied by an oversight about SID training paradigm. In this paper, we re-examine the SID problem and identify two prevalent biases in current training paradigms, i.e., weakened artifact features and overfitted artifact features. Meanwhile, we discover that the imaging mechanism of synthetic images contributes to heightened local correlations among pixels, suggesting that detectors should be equipped with local awareness. In this light, we propose SAFE, a lightweight and effective detector with three simple image transformations. Firstly, for weakened artifact features, we substitute the down-sampling operator with the crop operator in image pre-processing to help circumvent artifact distortion. Secondly, for overfitted artifact features, we include ColorJitter and RandomRotation as additional data augmentations, to help alleviate irrelevant biases from color discrepancies and semantic differences in limited training samples. Thirdly, for local awareness, we propose a patch-based random masking strategy tailored for SID, forcing the detector to focus on local regions at training. Comparative experiments are conducted on an open-world dataset, comprising synthetic images generated by 26 distinct generative models. Our pipeline achieves a new state-of-the-art performance, with remarkable improvements of 4.5% in accuracy and 2.9% in average precision against existing methods. Our code is available at: https://github.com/Ouxiang-Li/SAFE.

Ouxiang Li, Yanbin Hao, Zhicai Wang et al.

Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. To alleviate these issues, leveraging on diffusion models' remarkable synthesis capabilities, we propose Diffusion-based Model Inversion (Diff-MI) attacks. Specifically, we introduce a novel target-specific conditional diffusion model (CDM) to purposely approximate target classifier's private distribution and achieve superior accuracy-fidelity balance. Our method involves a two-step learning paradigm. Step-1 incorporates the target classifier into the entire CDM learning under a pretrain-then-finetune fashion, with creating pseudo-labels as model conditions in pretraining and adjusting specified layers with image predictions in fine-tuning. Step-2 presents an iterative image reconstruction method, further enhancing the attack performance through a combination of diffusion priors and target knowledge. Additionally, we propose an improved max-margin loss that replaces the hard max with top-k maxes, fully leveraging feature information and soft labels from the target classifier. Extensive experiments demonstrate that Diff-MI significantly improves generative fidelity with an average decrease of 20\% in FID while maintaining competitive attack accuracy compared to state-of-the-art methods across various datasets and models. Our code is available at: \url{https://github.com/Ouxiang-Li/Diff-MI}.

Yanbin Hao, Diansong Zhou, Zhicai Wang et al.

In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks. However, their inherently dense computational operators, such as self-attention and token-mixing layers, pose significant challenges when applied to spatio-temporal video data. To address this gap, we propose PosMLP-Video, a lightweight yet powerful MLP-like backbone for video recognition. Instead of dense operators, we use efficient relative positional encoding (RPE) to build pairwise token relations, leveraging small-sized parameterized relative position biases to obtain each relation score. Specifically, to enable spatio-temporal modeling, we extend the image PosMLP's positional gating unit to temporal, spatial, and spatio-temporal variants, namely PoTGU, PoSGU, and PoSTGU, respectively. These gating units can be feasibly combined into three types of spatio-temporal factorized positional MLP blocks, which not only decrease model complexity but also maintain good performance. Additionally, we enrich relative positional relationships by using channel grouping. Experimental results on three video-related tasks demonstrate that PosMLP-Video achieves competitive speed-accuracy trade-offs compared to the previous state-of-the-art models. In particular, PosMLP-Video pre-trained on ImageNet1K achieves 59.0%/70.3% top-1 accuracy on Something-Something V1/V2 and 82.1% top-1 accuracy on Kinetics-400 while requiring much fewer parameters and FLOPs than other models. The code is released at https://github.com/zhouds1918/PosMLP_Video.

Yi Tan, Zhaofan Qiu, Yanbin Hao et al.

The recent advances in Convolutional Neural Networks (CNNs) and Vision Transformers have convincingly demonstrated high learning capability for video action recognition on large datasets. Nevertheless, deep models often suffer from the overfitting effect on small-scale datasets with a limited number of training videos. A common solution is to exploit the existing image augmentation strategies for each frame individually including Mixup, Cutmix, and RandAugment, which are not particularly optimized for video data. In this paper, we propose a novel video augmentation strategy named Selective Volume Mixup (SV-Mix) to improve the generalization ability of deep models with limited training videos. SV-Mix devises a learnable selective module to choose the most informative volumes from two videos and mixes the volumes up to achieve a new training video. Technically, we propose two new modules, i.e., a spatial selective module to select the local patches for each spatial position, and a temporal selective module to mix the entire frames for each timestamp and maintain the spatial pattern. At each time, we randomly choose one of the two modules to expand the diversity of training samples. The selective modules are jointly optimized with the video action recognition framework to find the optimal augmentation strategy. We empirically demonstrate the merits of the SV-Mix augmentation on a wide range of video action recognition benchmarks and consistently boot the performances of both CNN-based and transformer-based models.

Yuhang Zhang, Junxiang Qiu, Huixia Ben et al.

Diffusion Transformers (DiTs) achieve strong visual quality, but their iterative denoising process requires many costly Transformer evaluations. Training-free acceleration methods reduce this cost by caching, forecasting, or verifying intermediate features, yet the runtime decision of when to execute a Full step is often driven by fixed schedules or hand-tuned thresholds. We propose \textbf{SoftCap}, a training-free control layer for cache-based DiT inference. SoftCap couples a Trajectory Drift Observer, which estimates local cache risk from lightweight hidden-state statistics, with a Soft-Budget PI Controller, which adjusts the Full-triggering threshold from realized compute relative to a fixed reference profile. The budget is a soft ceiling: it shapes the threshold but does not require a run to spend a prescribed number of Full evaluations. On FLUX.1-dev, SoftCap improves over SpeCa at a comparable middle-compute operating point, raising ImageReward from 0.967 to 0.981 and reducing LPIPS-Full from 0.518 to 0.498 at nearly identical FLOPs, while target-sweep diagnostics show the intended soft-ceiling behavior as the budget is relaxed.

Zhicai Wang, Longhui Wei, Tan Wang et al.

Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications. However, the effective integration of T2I models into fundamental image classification tasks remains an open question. A prevalent strategy to bolster image classification performance is through augmenting the training set with synthetic images generated by T2I models. In this study, we scrutinize the shortcomings of both current generative and conventional data augmentation techniques. Our analysis reveals that these methods struggle to produce images that are both faithful (in terms of foreground objects) and diverse (in terms of background contexts) for domain-specific concepts. To tackle this challenge, we introduce an innovative inter-class data augmentation method known as Diff-Mix (https://github.com/Zhicaiwww/Diff-Mix), which enriches the dataset by performing image translations between classes. Our empirical results demonstrate that Diff-Mix achieves a better balance between faithfulness and diversity, leading to a marked improvement in performance across diverse image classification scenarios, including few-shot, conventional, and long-tail classifications for domain-specific datasets.

Haoran Li, XiaoLu Li, Yihang Lin et al.

Video prediction is a complex time-series forecasting task with great potential in many use cases. However, traditional methods prioritize accuracy and overlook slow prediction speeds due to complex model structures, redundant information, and excessive GPU memory consumption. These methods often predict frames sequentially, making acceleration difficult and limiting their applicability in real-time scenarios like danger prediction and warning.Therefore, we propose a transformer-based keypoint prediction neural network (TKN). TKN extracts dynamic content from video frames in an unsupervised manner, reducing redundant feature computation. And, TKN uses an acceleration matrix to reduce the computational cost of attention and employs a parallel computing structure for prediction acceleration. To the best of our knowledge, TKN is the first real-time video prediction solution that achieves a prediction rate of 1,176 fps, significantly reducing computation costs while maintaining other performance. Qualitative and quantitative experiments on multiple datasets have demonstrated the superiority of our method, suggesting that TKN has great application potential.

Haozhuo Zhang, Bin Zhu, Yu Cao et al.

Text-to-image generation models have achieved remarkable advancements in recent years, aiming to produce realistic images from textual descriptions. However, these models often struggle with generating anatomically accurate representations of human hands. The resulting images frequently exhibit issues such as incorrect numbers of fingers, unnatural twisting or interlacing of fingers, or blurred and indistinct hands. These issues stem from the inherent complexity of hand structures and the difficulty in aligning textual descriptions with precise visual depictions of hands. To address these challenges, we propose a novel approach named Hand1000 that enables the generation of realistic hand images with target gesture using only 1,000 training samples. The training of Hand1000 is divided into three stages with the first stage aiming to enhance the model's understanding of hand anatomy by using a pre-trained hand gesture recognition model to extract gesture representation. The second stage further optimizes text embedding by incorporating the extracted hand gesture representation, to improve alignment between the textual descriptions and the generated hand images. The third stage utilizes the optimized embedding to fine-tune the Stable Diffusion model to generate realistic hand images. In addition, we construct the first publicly available dataset specifically designed for text-to-hand image generation. Based on the existing hand gesture recognition dataset, we adopt advanced image captioning models and LLaMA3 to generate high-quality textual descriptions enriched with detailed gesture information. Extensive experiments demonstrate that Hand1000 significantly outperforms existing models in producing anatomically correct hand images while faithfully representing other details in the text, such as faces, clothing, and colors.

Xingyu Zhu, Beier Zhu, Yi Tan et al.

Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. While optimizing prompts on downstream labeled data has proven effective in improving performance, these methods entail labor costs for annotations and are limited by their quality. Additionally, since CLIP is pre-trained on highly imbalanced Web-scale data, it suffers from inherent label bias that leads to suboptimal performance. To tackle the above challenges, we propose a label-Free prompt distribution learning and bias correction framework, dubbed as **Frolic**, which boosts zero-shot performance without the need for labeled data. Specifically, our Frolic learns distributions over prompt prototypes to capture diverse visual representations and adaptively fuses these with the original CLIP through confidence matching. This fused model is further enhanced by correcting label bias via a label-free logit adjustment. Notably, our method is not only training-free but also circumvents the necessity for hyper-parameter tuning. Extensive experimental results across 16 datasets demonstrate the efficacy of our approach, particularly outperforming the state-of-the-art by an average of $2.6\%$ on 10 datasets with CLIP ViT-B/16 and achieving an average margin of $1.5\%$ on ImageNet and its five distribution shifts with CLIP ViT-B/16. Codes are available in https://github.com/zhuhsingyuu/Frolic.

Ouxiang Li, Yuan Wang, Xinting Hu et al.

Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications, fine-tuning-based methods are time-consuming to precisely erase multiple target concepts, while real-time editing-based methods often degrade the generation quality of non-target concepts due to conflicting optimization objectives. To address this dilemma, we introduce SPEED, an efficient concept erasure approach that directly edits model parameters. SPEED searches for a null space, a model editing space where parameter updates do not affect non-target concepts, to achieve scalable and precise erasure. To facilitate accurate null space optimization, we incorporate three complementary strategies: Influence-based Prior Filtering (IPF) to selectively retain the most affected non-target concepts, Directed Prior Augmentation (DPA) to enrich the filtered retain set with semantically consistent variations, and Invariant Equality Constraints (IEC) to preserve key invariants during the T2I generation process. Extensive evaluations across multiple concept erasure tasks demonstrate that SPEED consistently outperforms existing methods in non-target preservation while achieving efficient and high-fidelity concept erasure, successfully erasing 100 concepts within only 5 seconds. Our code and models are available at: https://github.com/Ouxiang-Li/SPEED.

Haoran Li, Long Ma, Haolin Shi et al.

The current GAN inversion methods typically can only edit the appearance and shape of a single object and background while overlooking spatial information. In this work, we propose a 3D editing framework, 3D-GOI, to enable multifaceted editing of affine information (scale, translation, and rotation) on multiple objects. 3D-GOI realizes the complex editing function by inverting the abundance of attribute codes (object shape/appearance/scale/rotation/translation, background shape/appearance, and camera pose) controlled by GIRAFFE, a renowned 3D GAN. Accurately inverting all the codes is challenging, 3D-GOI solves this challenge following three main steps. First, we segment the objects and the background in a multi-object image. Second, we use a custom Neural Inversion Encoder to obtain coarse codes of each object. Finally, we use a round-robin optimization algorithm to get precise codes to reconstruct the image. To the best of our knowledge, 3D-GOI is the first framework to enable multifaceted editing on multiple objects. Both qualitative and quantitative experiments demonstrate that 3D-GOI holds immense potential for flexible, multifaceted editing in complex multi-object scenes.Our project and code are released at https://3d-goi.github.io .

Yuan Wang, Ouxiang Li, Tingting Mu et al.

Recent success of text-to-image (T2I) generation and its increasing practical applications, enabled by diffusion models, require urgent consideration of erasing unwanted concepts, e.g., copyrighted, offensive, and unsafe ones, from the pre-trained models in a precise, timely, and low-cost manner. The twofold demand of concept erasure includes not only a precise removal of the target concept (i.e., erasure efficacy) but also a minimal change on non-target content (i.e., prior preservation), during generation. Existing methods face challenges in maintaining an effective balance between erasure efficacy and prior preservation, and they can be computationally costly. To improve, we propose a precise, fast, and low-cost concept erasure method, called Adaptive Value Decomposer (AdaVD), which is training-free. Our method is grounded in a classical linear algebraic operation of computing the orthogonal complement, implemented in the value space of each cross-attention layer within the UNet of diffusion models. We design a shift factor to adaptively navigate the erasure strength, enhancing effective prior preservation without sacrificing erasure efficacy. Extensive comparative experiments with both training-based and training-free state-of-the-art methods demonstrate that the proposed AdaVD excels in both single and multiple concept erasure, showing 2 to 10 times improvement in prior preservation than the second best, meanwhile achieving the best or near best erasure efficacy. AdaVD supports a series of diffusion models and downstream image generation tasks, with code available on: https://github.com/WYuan1001/AdaVD.

Jinda Lu, Shuo Wang, Yanbin Hao et al.

Recent adaptations can boost the low-shot capability of Contrastive Vision-Language Pre-training (CLIP) by effectively facilitating knowledge transfer. However, these adaptation methods are usually operated on the global view of an input image, and thus biased perception of partial local details of the image. To solve this problem, we propose a Visual Content Refinement (VCR) before the adaptation calculation during the test stage. Specifically, we first decompose the test image into different scales to shift the feature extractor's attention to the details of the image. Then, we select the image view with the max prediction margin in each scale to filter out the noisy image views, where the prediction margins are calculated from the pre-trained CLIP model. Finally, we merge the content of the aforementioned selected image views based on their scales to construct a new robust representation. Thus, the merged content can be directly used to help the adapter focus on both global and local parts without any extra training parameters. We apply our method to 3 popular low-shot benchmark tasks with 13 datasets and achieve a significant improvement over state-of-the-art methods. For example, compared to the baseline (Tip-Adapter) on the few-shot classification task, our method achieves about 2\% average improvement for both training-free and training-need settings.

Junxiang Qiu, Shuo Wang, Jinda Lu et al.

Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time consumption of sampling. Existing caching methods accelerate generation by reusing DiT features from the previous time step and skipping calculations in the next, but they tend to locate and cache low-error modules without focusing on reducing caching-induced errors, resulting in a sharp decline in generated content quality when increasing caching intensity. To solve this problem, we propose the \textbf{E}rror-\textbf{O}ptimized \textbf{C}ache (\textbf{EOC}). This method introduces three key improvements: \textbf{(1)} Prior knowledge extraction: Extract and process the caching differences; \textbf{(2)} A judgment method for cache optimization: Determine whether certain caching steps need to be optimized; \textbf{(3)} Cache optimization: reduce caching errors. Experiments show that this algorithm significantly reduces the error accumulation caused by caching, especially excessive caching. On the ImageNet dataset, without substantially increasing the computational load, this method improves the FID of the generated images when the rule-based model FORA has a caching level of \textbf{75}\%, \textbf{50}\%, and \textbf{25}\%, and the training-based model Learning-to-cache has a caching level of \textbf{22}\%. Specifically, the FID values change from 30.454 to 21.690 (\textbf{28.8}\%), from 6.857 to 5.821 (\textbf{15.1}\%), from 3.870 to 3.692 (\textbf{4.6}\%), and from 3.539 to 3.451 (\textbf{2.5}\%) respectively. Code is available at https://github.com/qiujx0520/EOC_MM2025.git.

Junxiang Qiu, Lin Liu, Shuo Wang et al.

Feature caching has emerged as an effective strategy to accelerate diffusion transformer (DiT) sampling through temporal feature reuse. It is a challenging problem since (1) Progressive error accumulation from cached blocks significantly degrades generation quality, particularly when over 50\% of blocks are cached; (2) Current error compensation approaches neglect dynamic perturbation patterns during the caching process, leading to suboptimal error correction. To solve these problems, we propose the Gradient-Optimized Cache (GOC) with two key innovations: (1) Cached Gradient Propagation: A gradient queue dynamically computes the gradient differences between cached and recomputed features. These gradients are weighted and propagated to subsequent steps, directly compensating for the approximation errors introduced by caching. (2) Inflection-Aware Optimization: Through statistical analysis of feature variation patterns, we identify critical inflection points where the denoising trajectory changes direction. By aligning gradient updates with these detected phases, we prevent conflicting gradient directions during error correction. Extensive evaluations on ImageNet demonstrate GOC's superior trade-off between efficiency and quality. With 50\% cached blocks, GOC achieves IS 216.28 (26.3\% higher) and FID 3.907 (43\% lower) compared to baseline DiT, while maintaining identical computational costs. These improvements persist across various cache ratios, demonstrating robust adaptability to different acceleration requirements. Code is available at https://github.com/qiujx0520/GOC_ICCV2025.git.

Jinke Li, Jiarui Yu, Chenxing Wei et al.

Unlike bitmap images, scalable vector graphics (SVG) maintain quality when scaled, frequently employed in computer vision and artistic design in the representation of SVG code. In this era of proliferating AI-powered systems, enabling AI to understand and generate SVG has become increasingly urgent. However, AI-driven SVG understanding and generation (U&G) remain significant challenges. SVG code, equivalent to a set of curves and lines controlled by floating-point parameters, demands high precision in SVG U&G. Besides, SVG generation operates under diverse conditional constraints, including textual prompts and visual references, which requires powerful multi-modal processing for condition-to-SVG transformation. Recently, the rapid growth of Multi-modal Large Language Models (MLLMs) have demonstrated capabilities to process multi-modal inputs and generate complex vector controlling parameters, suggesting the potential to address SVG U&G tasks within a unified model. To unlock MLLM's capabilities in the SVG area, we propose an SVG-centric dataset called UniSVG, comprising 525k data items, tailored for MLLM training and evaluation. To our best knowledge, it is the first comprehensive dataset designed for unified SVG generation (from textual prompts and images) and SVG understanding (color, category, usage, etc.). As expected, learning on the proposed dataset boosts open-source MLLMs' performance on various SVG U&G tasks, surpassing SOTA close-source MLLMs like GPT-4V. We release dataset, benchmark, weights, codes and experiment details on https://ryanlijinke.github.io/.

Lin Liu, Huixia Ben, Shuo Wang et al.

Controllable generative models have been widely used to improve the realism of synthetic visual content. However, such models must handle control conditions and content generation computational requirements, resulting in generally low generation efficiency. To address this issue, we propose a Hybrid-Grained Cache (HGC) approach that reduces computational overhead by adopting cache strategies with different granularities at different computational stages. Specifically, (1) we use a coarse-grained cache (block-level) based on feature reuse to dynamically bypass redundant computations in encoder-decoder blocks between each step of model reasoning. (2) We design a fine-grained cache (prompt-level) that acts within a module, where the fine-grained cache reuses cross-attention maps within consecutive reasoning steps and extends them to the corresponding module computations of adjacent steps. These caches of different granularities can be seamlessly integrated into each computational link of the controllable generation process. We verify the effectiveness of HGC on four benchmark datasets, especially its advantages in balancing generation efficiency and visual quality. For example, on the COCO-Stuff segmentation benchmark, our HGC significantly reduces the computational cost (MACs) by 63% (from 18.22T to 6.70T), while keeping the loss of semantic fidelity (quantized performance degradation) within 1.5%.

Yuan Wang, Bin Zhu, Yanbin Hao et al.

Recent advancements in text-to-image generation models have excelled in creating diverse and realistic images. This success extends to food imagery, where various conditional inputs like cooking styles, ingredients, and recipes are utilized. However, a yet-unexplored challenge is generating a sequence of procedural images based on cooking steps from a recipe. This could enhance the cooking experience with visual guidance and possibly lead to an intelligent cooking simulation system. To fill this gap, we introduce a novel task called \textbf{cooking procedural image generation}. This task is inherently demanding, as it strives to create photo-realistic images that align with cooking steps while preserving sequential consistency. To collectively tackle these challenges, we present \textbf{CookingDiffusion}, a novel approach that leverages Stable Diffusion and three innovative Memory Nets to model procedural prompts. These prompts encompass text prompts (representing cooking steps), image prompts (corresponding to cooking images), and multi-modal prompts (mixing cooking steps and images), ensuring the consistent generation of cooking procedural images. To validate the effectiveness of our approach, we preprocess the YouCookII dataset, establishing a new benchmark. Our experimental results demonstrate that our model excels at generating high-quality cooking procedural images with remarkable consistency across sequential cooking steps, as measured by both the FID and the proposed Average Procedure Consistency metrics. Furthermore, CookingDiffusion demonstrates the ability to manipulate ingredients and cooking methods in a recipe. We will make our code, models, and dataset publicly accessible.

Fangwen Wu, Jingxuan He, Yufei Yin et al.

This study introduces an efficacious approach, Masked Collaborative Contrast (MCC), to highlight semantic regions in weakly supervised semantic segmentation. MCC adroitly draws inspiration from masked image modeling and contrastive learning to devise a novel framework that induces keys to contract toward semantic regions. Unlike prevalent techniques that directly eradicate patch regions in the input image when generating masks, we scrutinize the neighborhood relations of patch tokens by exploring masks considering keys on the affinity matrix. Moreover, we generate positive and negative samples in contrastive learning by utilizing the masked local output and contrasting it with the global output. Elaborate experiments on commonly employed datasets evidences that the proposed MCC mechanism effectively aligns global and local perspectives within the image, attaining impressive performance. The source code is available at \url{https://github.com/fwu11/MCC}.

Hao Zhang, Yanbin Hao, Chong-Wah Ngo

Transformer achieves remarkable successes in understanding 1 and 2-dimensional signals (e.g., NLP and Image Content Understanding). As a potential alternative to convolutional neural networks, it shares merits of strong interpretability, high discriminative power on hyper-scale data, and flexibility in processing varying length inputs. However, its encoders naturally contain computational intensive operations such as pair-wise self-attention, incurring heavy computational burden when being applied on the complex 3-dimensional video signals. This paper presents Token Shift Module (i.e., TokShift), a novel, zero-parameter, zero-FLOPs operator, for modeling temporal relations within each transformer encoder. Specifically, the TokShift barely temporally shifts partial [Class] token features back-and-forth across adjacent frames. Then, we densely plug the module into each encoder of a plain 2D vision transformer for learning 3D video representation. It is worth noticing that our TokShift transformer is a pure convolutional-free video transformer pilot with computational efficiency for video understanding. Experiments on standard benchmarks verify its robustness, effectiveness, and efficiency. Particularly, with input clips of 8/12 frames, the TokShift transformer achieves SOTA precision: 79.83%/80.40% on the Kinetics-400, 66.56% on EGTEA-Gaze+, and 96.80% on UCF-101 datasets, comparable or better than existing SOTA convolutional counterparts. Our code is open-sourced in: https://github.com/VideoNetworks/TokShift-Transformer.

Zhenguang Liu, Kedi Lyu, Shuang Wu et al.

Human motion prediction from historical pose sequence is at the core of many applications in machine intelligence. However, in current state-of-the-art methods, the predicted future motion is confined within the same activity. One can neither generate predictions that differ from the current activity, nor manipulate the body parts to explore various future possibilities. Undoubtedly, this greatly limits the usefulness and applicability of motion prediction. In this paper, we propose a generalization of the human motion prediction task in which control parameters can be readily incorporated to adjust the forecasted motion. Our method is compelling in that it enables manipulable motion prediction across activity types and allows customization of the human movement in a variety of fine-grained ways. To this aim, a simple yet effective composite GAN structure, consisting of local GANs for different body parts and aggregated via a global GAN is presented. The local GANs game in lower dimensions, while the global GAN adjusts in high dimensional space to avoid mode collapse. Extensive experiments show that our method outperforms state-of-the-art. The codes are available at https://github.com/herolvkd/AM-GAN.

Pengyuan Zhou, Lin Wang, Zhi Liu et al.

This paper offers an insightful examination of how currently top-trending AI technologies, i.e., generative artificial intelligence (Generative AI) and large language models (LLMs), are reshaping the field of video technology, including video generation, understanding, and streaming. It highlights the innovative use of these technologies in producing highly realistic videos, a significant leap in bridging the gap between real-world dynamics and digital creation. The study also delves into the advanced capabilities of LLMs in video understanding, demonstrating their effectiveness in extracting meaningful information from visual content, thereby enhancing our interaction with videos. In the realm of video streaming, the paper discusses how LLMs contribute to more efficient and user-centric streaming experiences, adapting content delivery to individual viewer preferences. This comprehensive review navigates through the current achievements, ongoing challenges, and future possibilities of applying Generative AI and LLMs to video-related tasks, underscoring the immense potential these technologies hold for advancing the field of video technology related to multimedia, networking, and AI communities.

Xingyu Zhu, Shuo Wang, Jinda Lu et al.

Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor. However, this mixing operation weakens the feature representation due to the linear interpolation and the overlooking of the importance of specific channels. To solve these issues, this paper proposes attentive feature regularization (AFR) which aims to improve the feature representativeness and discriminability. In our approach, we first calculate the relations between different categories of semantic labels to pick out the related features used for regularization. Then, we design two attention-based calculations at both the instance and channel levels. These calculations enable the regularization procedure to focus on two crucial aspects: the feature complementarity through adaptive interpolation in related categories and the emphasis on specific feature channels. Finally, we combine these regularization strategies to significantly improve the classifier performance. Empirical studies on several popular FSL benchmarks demonstrate the effectiveness of AFR, which improves the recognition accuracy of novel categories without the need to retrain any feature extractor, especially in the 1-shot setting. Furthermore, the proposed AFR can seamlessly integrate into other FSL methods to improve classification performance.

Qinglong Huang, Haoran Li, Yong Liao et al.

Neural Radiance Field (NeRF) has been proposed as an innovative advancement in 3D reconstruction techniques. However, little research has been conducted on the issues of information confidentiality and security to NeRF, such as steganography. Existing NeRF steganography solutions have shortcomings in low steganography quality, model weight damage, and limited amount of steganographic information. This paper proposes Noise-NeRF, a novel NeRF steganography method employing Adaptive Pixel Selection strategy and Pixel Perturbation strategy to improve the quality and efficiency of steganography via trainable noise. Extensive experiments validate the state-of-the-art performances of Noise-NeRF on both steganography quality and rendering quality, as well as effectiveness in super-resolution image steganography.

Bob Zhang, Haoran Li, Tao Zhang et al.

Recently, Multimodal Large Language Models (MLLMs) excel at visual grounding in single-image scenarios with textual references. However, their performance degrades when handling real-world applications that involve complex multi-image compositions and multi-modal instructions, revealing limitations in cross-image reasoning and generalization. To address these challenges, we adopt a Reinforcement Learning (RL) based post-training strategy to improve the reasoning of MLLMs in multi-image grounding tasks. Our approach begins with synthesizing high-quality chain-of-thought (CoT) data for cold-start initialization, followed by supervised fine-tuning (SFT) using low-rank adaptation (LoRA). The cold-start training stage enables the model to identify correct solutions. Subsequently, we perform rejection sampling using the merged SFT model to curate high-quality RL data and leverage rule-based RL to guide the model toward optimal reasoning paths. Extensive experimental results demonstrate the effectiveness of our approach, yielding improvements of +9.04% on MIG-Bench, +6.37% on MC-Bench, and +4.98% on several out-of-domain reasoning grounding benchmarks compared to the SFT baseline. Furthermore, our method exhibits strong generalization in multi-image perception, with gains of +3.1% and +2.4% over the base model on BLINK and MMIU benchmarks, respectively.

Yuan Sheng, Yanbin Hao, Chenxu Li et al.

Long video understanding remains challenging due to its complex, diverse, and temporally scattered content. Although video large language models (Video-LLMs) can process videos lasting tens of minutes, applying them to truly long sequences is computationally prohibitive and often leads to unfocused or inconsistent reasoning. A promising solution is to select only the most informative frames, yet existing approaches typically ignore temporal dependencies or rely on unimodal evidence, limiting their ability to provide complete and query-relevant context. We propose a Semantic-Visual Consensus Evidence Selection (SeViCES) framework for effective and reliable long video understanding. SeViCES is training-free and model-agnostic, and introduces two key components. The Semantic-Visual Consensus Frame Selection (SVCFS) module selects frames through (1) a temporal-aware semantic branch that leverages LLM reasoning over captions, and (2) a cluster-guided visual branch that aligns embeddings with semantic scores via mutual information. The Answer Consensus Refinement (ACR) module further resolves inconsistencies between semantic- and visual-based predictions by fusing evidence and constraining the answer space. Extensive experiments on long video understanding benchmarks show that SeViCES consistently outperforms state-of-the-art methods in both accuracy and robustness, demonstrating the importance of consensus-driven evidence selection for Video-LLMs.

Chenxu Li, Zhicai Wang, Yuan Sheng et al.

Multimodal Large Language Models (MLLMs) increasingly support dynamic image resolutions. However, current evaluation paradigms primarily assess semantic performance, overlooking the critical question of resolution robustness - whether performance remains stable across varying input resolutions. To address this gap, we introduce \textbf{Res-Bench}, a comprehensive benchmark comprising 14,400 samples across 12 resolution levels and six core capability dimensions. We designed a novel evaluation framework that goes beyond traditional accuracy metrics to capture performance stability. This framework introduces multiple robustness metrics: Spearman's correlation for assessing resolution-performance trends, and Absolute/Relative Continuous Error (ACE/RCE) for measuring performance volatility. Using these metrics, we conducted a large-scale evaluation of leading MLLMs. Our analysis encompasses: (1) model-centric and task-centric robustness examination, (2) investigation of preprocessing strategies including padding and super-resolution, and (3) exploration of fine-tuning for stability enhancement.

Shilin Yan, Ouxiang Li, Jiayin Cai et al.

With the rapid development of generative models, discerning AI-generated content has evoked increasing attention from both industry and academia. In this paper, we conduct a sanity check on "whether the task of AI-generated image detection has been solved". To start with, we present Chameleon dataset, consisting AIgenerated images that are genuinely challenging for human perception. To quantify the generalization of existing methods, we evaluate 9 off-the-shelf AI-generated image detectors on Chameleon dataset. Upon analysis, almost all models classify AI-generated images as real ones. Later, we propose AIDE (AI-generated Image DEtector with Hybrid Features), which leverages multiple experts to simultaneously extract visual artifacts and noise patterns. Specifically, to capture the high-level semantics, we utilize CLIP to compute the visual embedding. This effectively enables the model to discern AI-generated images based on semantics or contextual information; Secondly, we select the highest frequency patches and the lowest frequency patches in the image, and compute the low-level patchwise features, aiming to detect AI-generated images by low-level artifacts, for example, noise pattern, anti-aliasing, etc. While evaluating on existing benchmarks, for example, AIGCDetectBenchmark and GenImage, AIDE achieves +3.5% and +4.6% improvements to state-of-the-art methods, and on our proposed challenging Chameleon benchmarks, it also achieves the promising results, despite this problem for detecting AI-generated images is far from being solved.

Haihong Hao, Shuo Wang, Huixia Ben et al.

Micro-expression recognition (MER) aims to recognize the short and subtle facial movements from the Micro-expression (ME) video clips, which reveal real emotions. Recent MER methods mostly only utilize special frames from ME video clips or extract optical flow from these special frames. However, they neglect the relationship between movements and space-time, while facial cues are hidden within these relationships. To solve this issue, we propose the Hierarchical Space-Time Attention (HSTA). Specifically, we first process ME video frames and special frames or data parallelly by our cascaded Unimodal Space-Time Attention (USTA) to establish connections between subtle facial movements and specific facial areas. Then, we design Crossmodal Space-Time Attention (CSTA) to achieve a higher-quality fusion for crossmodal data. Finally, we hierarchically integrate USTA and CSTA to grasp the deeper facial cues. Our model emphasizes temporal modeling without neglecting the processing of special data, and it fuses the contents in different modalities while maintaining their respective uniqueness. Extensive experiments on the four benchmarks show the effectiveness of our proposed HSTA. Specifically, compared with the latest method on the CASME3 dataset, it achieves about 3% score improvement in seven-category classification.