ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding

We present ASAP, a new framework for detecting and grounding multi-modal media manipulation (DGM4).Upon thorough examination, we observe that accurate fine-grained cross-modal semantic alignment between the image and text is vital for accurately manipulation detection and grounding. While existing DGM4 methods pay rare attention to the cross-modal alignment, hampering the accuracy of manipulation detecting to step further. To remedy this issue, this work targets to advance the semantic alignment learning to promote this task. Particularly, we utilize the off-the-shelf Multimodal Large-Language Models (MLLMs) and Large Language Models (LLMs) to construct paired image-text pairs, especially for the manipulated instances. Subsequently, a cross-modal alignment learning is performed to enhance the semantic alignment. Besides the explicit auxiliary clues, we further design a Manipulation-Guided Cross Attention (MGCA) to provide implicit guidance for augmenting the manipulation perceiving. With the grounding truth available during training, MGCA encourages the model to concentrate more on manipulated components while downplaying normal ones, enhancing the model's ability to capture manipulations. Extensive experiments are conducted on the DGM4 dataset, the results demonstrate that our model can surpass the comparison method with a clear margin.

Repetitive Action Counting with Hybrid Temporal Relation Modeling

Repetitive Action Counting (RAC) aims to count the number of repetitive actions occurring in videos. In the real world, repetitive actions have great diversity and bring numerous challenges (e.g., viewpoint changes, non-uniform periods, and action interruptions). Existing methods based on the temporal self-similarity matrix (TSSM) for RAC are trapped in the bottleneck of insufficient capturing action periods when applied to complicated daily videos. To tackle this issue, we propose a novel method named Hybrid Temporal Relation Modeling Network (HTRM-Net) to build diverse TSSM for RAC. The HTRM-Net mainly consists of three key components: bi-modal temporal self-similarity matrix modeling, random matrix dropping, and local temporal context modeling. Specifically, we construct temporal self-similarity matrices by bi-modal (self-attention and dual-softmax) operations, yielding diverse matrix representations from the combination of row-wise and column-wise correlations. To further enhance matrix representations, we propose incorporating a random matrix dropping module to guide channel-wise learning of the matrix explicitly. After that, we inject the local temporal context of video frames and the learned matrix into temporal correlation modeling, which can make the model robust enough to cope with error-prone situations, such as action interruption. Finally, a multi-scale matrix fusion module is designed to aggregate temporal correlations adaptively in multi-scale matrices. Extensive experiments across intra- and cross-datasets demonstrate that the proposed method not only outperforms current state-of-the-art methods but also exhibits robust capabilities in accurately counting repetitive actions in unseen action categories. Notably, our method surpasses the classical TransRAC method by 20.04\% in MAE and 22.76\% in OBO.

Towards Pixel-Level Prediction for Gaze Following: Benchmark and Approach

Following the gaze of other people and analyzing the target they are looking at can help us understand what they are thinking, and doing, and predict the actions that may follow. Existing methods for gaze following struggle to perform well in natural scenes with diverse objects, and focus on gaze points rather than objects, making it difficult to deliver clear semantics and accurate scope of the targets. To address this shortcoming, we propose a novel gaze target prediction solution named GazeSeg, that can fully utilize the spatial visual field of the person as guiding information and lead to a progressively coarse-to-fine gaze target segmentation and recognition process. Specifically, a prompt-based visual foundation model serves as the encoder, working in conjunction with three distinct decoding modules (e.g. FoV perception, heatmap generation, and segmentation) to form the framework for gaze target prediction. Then, with the head bounding box performed as an initial prompt, GazeSeg obtains the FoV map, heatmap, and segmentation map progressively, leading to a unified framework for multiple tasks (e.g. direction estimation, gaze target segmentation, and recognition). In particular, to facilitate this research, we construct and release a new dataset, comprising 72k images with pixel-level annotations and 270 categories of gaze targets, built upon the GazeFollow dataset. The quantitative evaluation shows that our approach achieves the Dice of 0.325 in gaze target segmentation and 71.7% top-5 recognition. Meanwhile, our approach also outperforms previous state-of-the-art methods, achieving 0.953 in AUC on the gaze-following task. The dataset and code will be released.

LokiTalk: Learning Fine-Grained and Generalizable Correspondences to Enhance NeRF-based Talking Head Synthesis

Despite significant progress in talking head synthesis since the introduction of Neural Radiance Fields (NeRF), visual artifacts and high training costs persist as major obstacles to large-scale commercial adoption. We propose that identifying and establishing fine-grained and generalizable correspondences between driving signals and generated results can simultaneously resolve both problems. Here we present LokiTalk, a novel framework designed to enhance NeRF-based talking heads with lifelike facial dynamics and improved training efficiency. To achieve fine-grained correspondences, we introduce Region-Specific Deformation Fields, which decompose the overall portrait motion into lip movements, eye blinking, head pose, and torso movements. By hierarchically modeling the driving signals and their associated regions through two cascaded deformation fields, we significantly improve dynamic accuracy and minimize synthetic artifacts. Furthermore, we propose ID-Aware Knowledge Transfer, a plug-and-play module that learns generalizable dynamic and static correspondences from multi-identity videos, while simultaneously extracting ID-specific dynamic and static features to refine the depiction of individual characters. Comprehensive evaluations demonstrate that LokiTalk delivers superior high-fidelity results and training efficiency compared to previous methods. The code will be released upon acceptance.

Multimodal Crash Likelihood Prediction: A Complexity-Infused Approach Integrating Semantic, Contextual, and Driving Features

Predicting crash likelihood in complex driving environments is essential for improving traffic safety and advancing autonomous driving. Previous studies have used statistical models and deep learning to predict crashes based on semantic, contextual, or driving features, but none have examined the combined influence of these factors, termed roadway complexity in this study. This paper introduces a two-stage framework that integrates roadway complexity features for crash prediction. In the first stage, an encoder extracts hidden contextual information from these features, generating complexity-infused features. The second stage uses both original and complexity-infused features to predict crash likelihood, achieving an accuracy of 87.98% with original features alone and 90.15% with the added complexity-infused features. Ablation studies confirm that a combination of semantic, driving, and contextual features yields the best results, which emphasize their role in capturing roadway complexity. Additionally, complexity index annotations generated by Large Language Models outperform those by Amazon Mechanical Turk, highlighting the potential of automated tools for accurate, scalable crash prediction systems.

An Information-Theoretic Regularizer for Lossy Neural Image Compression

Lossy image compression networks aim to minimize the latent entropy of images while adhering to specific distortion constraints. However, optimizing the neural network can be challenging due to its nature of learning quantized latent representations. In this paper, our key finding is that minimizing the latent entropy is, to some extent, equivalent to maximizing the conditional source entropy, an insight that is deeply rooted in information-theoretic equalities. Building on this insight, we propose a novel structural regularization method for the neural image compression task by incorporating the negative conditional source entropy into the training objective, such that both the optimization efficacy and the model's generalization ability can be promoted. The proposed information-theoretic regularizer is interpretable, plug-and-play, and imposes no inference overheads. Extensive experiments demonstrate its superiority in regularizing the models and further squeezing bits from the latent representation across various compression structures and unseen domains.

Separable Mixture of Low-Rank Adaptation for Continual Visual Instruction Tuning

Visual instruction tuning (VIT) enables multimodal large language models (MLLMs) to effectively handle a wide range of vision tasks by framing them as language-based instructions. Building on this, continual visual instruction tuning (CVIT) extends the capability of MLLMs to incrementally learn new tasks, accommodating evolving functionalities. While prior work has advanced CVIT through the development of new benchmarks and approaches to mitigate catastrophic forgetting, these efforts largely follow traditional continual learning paradigms, neglecting the unique challenges specific to CVIT. We identify a dual form of catastrophic forgetting in CVIT, where MLLMs not only forget previously learned visual understanding but also experience a decline in instruction following abilities as they acquire new tasks. To address this, we introduce the Separable Mixture of Low-Rank Adaptation (SMoLoRA) framework, which employs separable routing through two distinct modules - one for visual understanding and another for instruction following. This dual-routing design enables specialized adaptation in both domains, preventing forgetting while improving performance. Furthermore, we propose a novel CVIT benchmark that goes beyond existing benchmarks by additionally evaluating a model's ability to generalize to unseen tasks and handle diverse instructions across various tasks. Extensive experiments demonstrate that SMoLoRA outperforms existing methods in mitigating dual forgetting, improving generalization to unseen tasks, and ensuring robustness in following diverse instructions.

Compact Visual Data Representation for Green Multimedia -- A Human Visual System Perspective

The Human Visual System (HVS), with its intricate sophistication, is capable of achieving ultra-compact information compression for visual signals. This remarkable ability is coupled with high generalization capability and energy efficiency. By contrast, the state-of-the-art Versatile Video Coding (VVC) standard achieves a compression ratio of around 1,000 times for raw visual data. This notable disparity motivates the research community to draw inspiration to effectively handle the immense volume of visual data in a green way. Therefore, this paper provides a survey of how visual data can be efficiently represented for green multimedia, in particular when the ultimate task is knowledge extraction instead of visual signal reconstruction. We introduce recent research efforts that promote green, sustainable, and efficient multimedia in this field. Moreover, we discuss how the deep understanding of the HVS can benefit the research community, and envision the development of future green multimedia technologies.

Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models

Knowledge editing aims to efficiently and cost-effectively correct inaccuracies and update outdated information. Recently, there has been growing interest in extending knowledge editing from Large Language Models (LLMs) to Multimodal Large Language Models (MLLMs), which integrate both textual and visual information, introducing additional editing complexities. Existing multimodal knowledge editing works primarily focus on text-oriented, coarse-grained scenarios, failing to address the unique challenges posed by multimodal contexts. In this paper, we propose a visual-oriented, fine-grained multimodal knowledge editing task that targets precise editing in images with multiple interacting entities. We introduce the Fine-Grained Visual Knowledge Editing (FGVEdit) benchmark to evaluate this task. Moreover, we propose a Multimodal Scope Classifier-based Knowledge Editor (MSCKE) framework. MSCKE leverages a multimodal scope classifier that integrates both visual and textual information to accurately identify and update knowledge related to specific entities within images. This approach ensures precise editing while preserving irrelevant information, overcoming the limitations of traditional text-only editing methods. Extensive experiments on the FGVEdit benchmark demonstrate that MSCKE outperforms existing methods, showcasing its effectiveness in solving the complex challenges of multimodal knowledge editing.

Towards Open-Vocabulary Audio-Visual Event Localization

The Audio-Visual Event Localization (AVEL) task aims to temporally locate and classify video events that are both audible and visible. Most research in this field assumes a closed-set setting, which restricts these models' ability to handle test data containing event categories absent (unseen) during training. Recently, a few studies have explored AVEL in an open-set setting, enabling the recognition of unseen events as ``unknown'', but without providing category-specific semantics. In this paper, we advance the field by introducing the Open-Vocabulary Audio-Visual Event Localization (OV-AVEL) problem, which requires localizing audio-visual events and predicting explicit categories for both seen and unseen data at inference. To address this new task, we propose the OV-AVEBench dataset, comprising 24,800 videos across 67 real-life audio-visual scenes (seen:unseen = 46:21), each with manual segment-level annotation. We also establish three evaluation metrics for this task. Moreover, we investigate two baseline approaches, one training-free and one using a further fine-tuning paradigm. Specifically, we utilize the unified multimodal space from the pretrained ImageBind model to extract audio, visual, and textual (event classes) features. The training-free baseline then determines predictions by comparing the consistency of audio-text and visual-text feature similarities. The fine-tuning baseline incorporates lightweight temporal layers to encode temporal relations within the audio and visual modalities, using OV-AVEBench training data for model fine-tuning. We evaluate these baselines on the proposed OV-AVEBench dataset and discuss potential directions for future work in this new field.