iFADIT: Invertible Face Anonymization via Disentangled Identity Transform

Face anonymization aims to conceal the visual identity of a face to safeguard the individual's privacy. Traditional methods like blurring and pixelation can largely remove identifying features, but these techniques significantly degrade image quality and are vulnerable to deep reconstruction attacks. Generative models have emerged as a promising solution for anonymizing faces while preserving a natural appearance.However, many still face limitations in visual quality and often overlook the potential to recover the original face from the anonymized version, which can be valuable in specific contexts such as image forensics. This paper proposes a novel framework named iFADIT, an acronym for Invertible Face Anonymization via Disentangled Identity Transform.The framework features a disentanglement architecture coupled with a secure flow-based model: the former decouples identity information from non-identifying attributes, while the latter transforms the decoupled identity into an anonymized version in an invertible manner controlled by a secret key. The anonymized face can then be reconstructed based on a pre-trained StyleGAN that ensures high image quality and realistic facial details. Recovery of the original face (aka de-anonymization) is possible upon the availability of the matching secret, by inverting the anonymization process based on the same set of model parameters. Furthermore, a dedicated secret-key mechanism along with a dual-phase training strategy is devised to ensure the desired properties of face anonymization. Qualitative and quantitative experiments demonstrate the superiority of the proposed approach in anonymity, reversibility, security, diversity, and interpretability over competing methods.

Online Video Understanding: A Comprehensive Benchmark and Memory-Augmented Method

Multimodal Large Language Models (MLLMs) have shown significant progress in offline video understanding. However, applying these models to real-world scenarios, such as autonomous driving and human-computer interaction, presents unique challenges due to the need for real-time processing of continuous online video streams. To this end, this paper presents systematic efforts from three perspectives: evaluation benchmark, model architecture, and training strategy. First, we introduce OVBench, a comprehensive question-answering benchmark specifically designed to evaluate models' ability to perceive, memorize, and reason within online video contexts. It features six core task types across three temporal contexts-past, present, and future-forming 16 subtasks from diverse datasets. Second, we propose a new Pyramid Memory Bank (PMB) that effectively retains key spatiotemporal information in video streams. Third, we proposed an offline-to-online learning paradigm, designing an interleaved dialogue format for online video data and constructing an instruction-tuning dataset tailored for online video training. This framework led to the development of VideoChat-Online, a robust and efficient model for online video understanding. Despite the lower computational cost and higher efficiency, VideoChat-Online outperforms existing state-of-the-art offline and online models across popular offline video benchmarks and OVBench, demonstrating the effectiveness of our model architecture and training strategy.

Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study

With the rise of multimodal large language models, accurately extracting and understanding textual information from video content, referred to as video based optical character recognition (Video OCR), has become a crucial capability. This paper introduces a novel benchmark designed to evaluate the video OCR performance of multi-modal models in videos. Comprising 1,028 videos and 2,961 question-answer pairs, this benchmark proposes several key challenges through 6 distinct subtasks: (1) Recognition of text content itself and its basic visual attributes, (2)Semantic and Spatial Comprehension of OCR objects in videos (3) Dynamic Motion detection and Temporal Localization. We developed this benchmark using a semi-automated approach that integrates the OCR ability of image LLMs with manual refinement, balancing efficiency, cost, and data quality. Our resource aims to help advance research in video LLMs and underscores the need for improving OCR ability for video LLMs. The benchmark will be released on https://github.com/YuHuiGao/FG-Bench.git.

VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models

Zero-shot customized video generation has gained significant attention due to its substantial application potential. Existing methods rely on additional models to extract and inject reference subject features, assuming that the Video Diffusion Model (VDM) alone is insufficient for zero-shot customized video generation. However, these methods often struggle to maintain consistent subject appearance due to suboptimal feature extraction and injection techniques. In this paper, we reveal that VDM inherently possesses the force to extract and inject subject features. Departing from previous heuristic approaches, we introduce a novel framework that leverages VDM's inherent force to enable high-quality zero-shot customized video generation. Specifically, for feature extraction, we directly input reference images into VDM and use its intrinsic feature extraction process, which not only provides fine-grained features but also significantly aligns with VDM's pre-trained knowledge. For feature injection, we devise an innovative bidirectional interaction between subject features and generated content through spatial self-attention within VDM, ensuring that VDM has better subject fidelity while maintaining the diversity of the generated video.Experiments on both customized human and object video generation validate the effectiveness of our framework.

NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries

The rapid advancement of Vision-Language Models (VLMs) has significantly advanced the development of Embodied Question Answering (EQA), enhancing agents' abilities in language understanding and reasoning within complex and realistic scenarios. However, EQA in real-world scenarios remains challenging, as human-posed questions often contain noise that can interfere with an agent's exploration and response, bringing challenges especially for language beginners and non-expert users. To address this, we introduce a NoisyEQA benchmark designed to evaluate an agent's ability to recognize and correct noisy questions. This benchmark introduces four common types of noise found in real-world applications: Latent Hallucination Noise, Memory Noise, Perception Noise, and Semantic Noise generated through an automated dataset creation framework. Additionally, we also propose a 'Self-Correction' prompting mechanism and a new evaluation metric to enhance and measure both noise detection capability and answer quality. Our comprehensive evaluation reveals that current EQA agents often struggle to detect noise in questions, leading to responses that frequently contain erroneous information. Through our Self-Correct Prompting mechanism, we can effectively improve the accuracy of agent answers.

p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay

Despite the remarkable performance of multimodal large language models (MLLMs) across diverse tasks, the substantial training and inference costs impede their advancement. The majority of computation stems from the overwhelming volume of vision tokens processed by the transformer decoder. In this paper, we propose to build efficient MLLMs by leveraging the Mixture-of-Depths (MoD) mechanism, where each transformer decoder layer selects essential vision tokens to process while skipping redundant ones. However, integrating MoD into MLLMs is non-trivial. To address the challenges of training and inference stability as well as limited training data, we adapt the MoD module with two novel designs: tanh-gated weight normalization (TanhNorm) and symmetric token reweighting (STRing). Moreover, we observe that vision tokens exhibit higher redundancy in deeper layer and thus design a progressive ratio decay (PRD) strategy, which gradually reduces the token retention ratio layer by layer, employing a shifted cosine schedule. This crucial design fully unleashes the potential of MoD, significantly boosting the efficiency and performance of our models. To validate the effectiveness of our approach, we conduct extensive experiments with two baseline models across 14 benchmarks. Our model, p-MoD, matches or even surpasses the performance of the baseline models, with only 55.6% TFLOPs and 53.8% KV cache storage during inference, and 77.7% GPU hours during training.

CamI2V: Camera-Controlled Image-to-Video Diffusion Model

Recently, camera pose, as a user-friendly and physics-related condition, has been introduced into text-to-video diffusion model for camera control. However, existing methods simply inject camera conditions through a side input. These approaches neglect the inherent physical knowledge of camera pose, resulting in imprecise camera control, inconsistencies, and also poor interpretability. In this paper, we emphasize the necessity of integrating explicit physical constraints into model design. Epipolar attention is proposed for modeling all cross-frame relationships from a novel perspective of noised condition. This ensures that features are aggregated from corresponding epipolar lines in all noised frames, overcoming the limitations of current attention mechanisms in tracking displaced features across frames, especially when features move significantly with the camera and become obscured by noise. Additionally, we introduce register tokens to handle cases without intersections between frames, commonly caused by rapid camera movements, dynamic objects, or occlusions. To support image-to-video, we propose the multiple guidance scale to allow for precise control for image, text, and camera, respectively. Furthermore, we establish a more robust and reproducible evaluation pipeline to solve the inaccuracy and instability of existing camera control measurement. We achieve a 25.5\% improvement in camera controllability on RealEstate10K while maintaining strong generalization to out-of-domain images. Only 24GB and 12GB are required for training and inference, respectively. We plan to release checkpoints, along with training and evaluation codes. Dynamic videos are best viewed at \url{https://zgctroy.github.io/CamI2V}.

Semantic Alignment for Multimodal Large Language Models

Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g., change captioning). Existing MLLMs typically follow a two-step process in their pipelines: first, extracting visual tokens independently for each input image, and then aligning these visual tokens from different images with the Large Language Model (LLM) in its textual feature space. However, the independent extraction of visual tokens for each image may result in different semantics being prioritized for different images in the first step, leading to a lack of preservation of linking information among images for subsequent LLM analysis. This issue becomes more serious in scenarios where significant variations exist among the images (e.g., visual storytelling). To address this challenge, we introduce Semantic Alignment for Multi-modal large language models (SAM). By involving the bidirectional semantic guidance between different images in the visual-token extraction process, SAM aims to enhance the preservation of linking information for coherent analysis and align the semantics of different images before feeding them into LLM. As the test bed, we propose a large-scale dataset named MmLINK consisting of 69K samples. Different from most existing datasets for MLLMs fine-tuning, our MmLINK dataset comprises multi-modal instructions with significantly diverse images. Extensive experiments on the group captioning task and the storytelling task prove the effectiveness of our SAM model, surpassing the state-of-the-art methods by a large margin (+37% for group captioning and +22% for storytelling on CIDEr score). Project page: https://mccartney01.github.io/SAM.

CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities

Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of video diffusion models (VDMs) to combine concepts and generate motions. To restore these abilities, some methods use additional video similar to the prompt to fine-tune or guide the model. This requires frequent changes of guiding videos and even re-tuning of the model when generating different motions, which is very inconvenient for users. In this paper, we propose CustomCrafter, a novel framework that preserves the model's motion generation and conceptual combination abilities without additional video and fine-tuning to recovery. For preserving conceptual combination ability, we design a plug-and-play module to update few parameters in VDMs, enhancing the model's ability to capture the appearance details and the ability of concept combinations for new subjects. For motion generation, we observed that VDMs tend to restore the motion of video in the early stage of denoising, while focusing on the recovery of subject details in the later stage. Therefore, we propose Dynamic Weighted Video Sampling Strategy. Using the pluggability of our subject learning modules, we reduce the impact of this module on motion generation in the early stage of denoising, preserving the ability to generate motion of VDMs. In the later stage of denoising, we restore this module to repair the appearance details of the specified subject, thereby ensuring the fidelity of the subject's appearance. Experimental results show that our method has a significant improvement compared to previous methods.

MacFormer: Semantic Segmentation with Fine Object Boundaries

Semantic segmentation involves assigning a specific category to each pixel in an image. While Vision Transformer-based models have made significant progress, current semantic segmentation methods often struggle with precise predictions in localized areas like object boundaries. To tackle this challenge, we introduce a new semantic segmentation architecture, ``MacFormer'', which features two key components. Firstly, using learnable agent tokens, a Mutual Agent Cross-Attention (MACA) mechanism effectively facilitates the bidirectional integration of features across encoder and decoder layers. This enables better preservation of low-level features, such as elementary edges, during decoding. Secondly, a Frequency Enhancement Module (FEM) in the decoder leverages high-frequency and low-frequency components to boost features in the frequency domain, benefiting object boundaries with minimal computational complexity increase. MacFormer is demonstrated to be compatible with various network architectures and outperforms existing methods in both accuracy and efficiency on benchmark datasets ADE20K and Cityscapes under different computational constraints.