ACM MM 2024 Papers

With the rise of large-scale language models (LLMs), it is currently popular and effective to convert multimodal information into text descriptions for multimodal multi-hop question answering. However, we argue that the current methods of multi-modal multi-hop question answering still mainly face two challenges: 1) The retrieved evidence containing a large amount of redundant information, inevitably leads to a significant drop in performance due to irrelevant information misleading the prediction. 2) The reasoning process without interpretable reasoning steps makes the model difficult to discover the logical errors for handling complex questions. To solve these problems, we propose a unified LLMs-based approach but without heavily relying on them due to the LLM's potential errors, and innovatively treat multimodal multi-hop question answering as a joint entailment tree generation and question answering problem. Specifically, we design a multi-task learning framework with a focus on facilitating common knowledge sharing across interpretability and prediction tasks while preventing task-specific errors from interfering with each other via mixture of experts. Afterward, we design an iterative feedback mechanism to further enhance both tasks by feeding back the results of the joint training to the LLM for regenerating entailment trees, aiming to iteratively refine the potential answer. Notably, our method has won the first place in the official leaderboard of WebQA (since April 10, 2024), and achieves competitive results on MultimodalQA.

Estimating 3D human poses from monocular images is an important research area with many practical applications. However, the depth ambiguity of 2D solutions limits their accuracy in actions where occlusion exits or where slight centroid shifts can result in significant 3D pose variations. In this paper, we introduce a novel multimodal approach to mitigate the depth ambiguity inherent in monocular solutions by integrating spatial-aware pressure information. We first establish a data collection system with a pressure mat and a monocular camera, and construct a large-scale multimodal human activity dataset comprising over 600,000 frames of motion data. Utilizing this dataset, we propose a pressure image reconstruction network to extract pressure priors from monocular images. Subsequently, we introduce a Transformer-based multimodal pose estimation network to combine pressure priors with monocular images, achieving a world mean per joint position error of 51.6mm, outperforming state-of-the-art methods. Extensive experiments demonstrate the effectiveness of our multimodal 3D human pose estimation method across various actions and joints, highlighting the significance of spatial-aware pressure in improving the accuracy of monocular-vision-based methods. Our dataset is available at: https://github.com/LishuangZhan/SATPose.

Interactive segmentation task (IS) aims at taking into account the influence of user preferences on the basis of general semantic segmentation in order to obtain the specific target-of-interest. Given the fact that most of the related algorithms generate a single mask only, the robustness of which might be constrained due to the diversity of user intention in the early interaction stage, namely the vague selection of object part/whole object/adherent object, especially when there's only one click. To handle this, we propose a novel framework called Diversified Interactive Segmentation Network (DISNet) in which we revisit the peculiarity of first-click: given an input image, DISNet outputs multiple candidate masks under the guidance of first-click only, then a Dual-attentional Mask Correction (DAMC) module is utilized to measure the complex mutual effect within first-click, all-clicks and image features. Moreover, we design a new sampling strategy to generate GT masks with rich semantic relations. Performance analysis plus adequate ablation studies has demonstrated the efficacy of our methods, which further exemplifies the decisive role of first-click in the realm of IS.

Collecting large-scale multi-label data with full labels is difficult for real-world scenarios. Many existing studies have tried to address the issue of missing labels caused by annotation but ignored the difficulties encountered during the annotation process. We find that the high annotation workload can be attributed to two reasons: (1) Annotators are required to identify labels on widely varying visual concepts. (2) Exhaustively annotating the entire dataset with all the labels becomes notably difficult and time-consuming. In this paper, we propose a new setting, i.e. block diagonal labels, to reduce the workload on both sides. The numerous categories can be divided into different subsets based on semantics and relevance. Each annotator can only focus on its own subset of labels so that only a small set of highly relevant labels are required to be annotated per image. To deal with the issue of such missing labels, we introduce a simple yet effective method that does not require any prior knowledge of the dataset. In practice, we propose an Adaptive Pseudo-Labeling method to predict the unknown labels with less noise. Formal analysis is conducted to evaluate the superiority of our setting. Extensive experiments are conducted to verify the effectiveness of our method on multiple widely used benchmarks.

In Video-based Facial Expression Recognition (V-FER), models are typically trained on closed-set datasets with a fixed number of known classes. However, these models struggle with unknown classes common in real-world scenarios. In this paper, we introduce a challenging Open-set Video-based Facial Expression Recognition (OV-FER) task, aiming to identify both known and new, unseen facial expressions. While existing approaches use large-scale vision-language models like CLIP to identify unseen classes, we argue that these methods may not adequately capture the subtle human expressions needed for OV-FER. To address this limitation, we propose a novel Human Expression-Sensitive Prompting (HESP) mechanism to significantly enhance CLIP's ability to model video-based facial expression details effectively. Our proposed HESP comprises three components: 1) a textual prompting module with learnable prompts to enhance CLIP's textual representation of both known and unknown emotions, 2) a visual prompting module that encodes temporal emotional information from video frames using expression-sensitive attention, equipping CLIP with a new visual modeling ability to extract emotion-rich information, and 3) an open-set multi-task learning scheme that promotes interaction between the textual and visual modules, improving the understanding of novel human emotions in video sequences. Extensive experiments conducted on four OV-FER task settings demonstrate that HESP can significantly boost CLIP's performance (a relative improvement of 17.93% on AUROC and 106.18% on OSCR) and outperform other state-of-the-art open-set video understanding methods by a large margin. Code is available at https://github.com/cosinehuang/HESP.

Bokeh is a wide-aperture optical effect that creates aesthetic blurring in photography. However, achieving this effect typically demands expensive professional equipment and expertise. To make such cinematic techniques more accessible, bokeh rendering aims to generate the desired bokeh effects from all-in-focus inputs captured by smartphones. Previous efforts in bokeh rendering primarily focus on static images. However, when extended to video inputs, these methods exhibit flicker and artifacts due to a lack of temporal consistency modeling. Meanwhile, they cannot utilize information like occluded objects from adjacent frames, which are necessary for bokeh rendering. Moreover, the difficulties of capturing all-in-focus and bokeh video pairs result in a shortage of data for training video bokeh models. To tackle these challenges, we propose the Video Bokeh Renderer (VBR), the model designed specifically for video bokeh rendering.VBR leverages implicit feature space alignment and aggregation to model temporal consistency and exploit complementary information from adjacent frames. On the data front, we introduce the first Synthetic Video Bokeh (SVB) dataset, synthesizing authentic bokeh effects using ray-tracing techniques. Furthermore, to improve the robustness of the model to inaccurate disparity maps, we employ a set of augmentation strategies to simulate corrupted disparity inputs during training. Experimental results on both synthetic and real-world data demonstrate the effectiveness of our method.

Advances in computer vision research enable human-like high-dimensional perceptual induction over analogical visual reasoning problems, such as Raven's Progressive Matrices (RPMs). In this paper, we propose a Hierarchical Perception and Predictive Analogy-Inference network (HP^2AI), consisting of three major components that tackle key challenges of RPM problems. Firstly, in view of the limited receptive fields of shallow networks in most existing RPM solvers, a perceptual encoder is proposed, consisting of a series of hierarchically coupled Patch Attention and Local Context (PALC) blocks, which could capture local attributes at early stages and capture the global panel layout at deep stages. Secondly, most methods seek for object-level similarities to map the context images directly to the answer image, while failing to extract the underlying analogies. The proposed reasoning module, Predictive Analogy-Inference (PredAI), consists of a set of Analogy-Inference Blocks (AIBs) to model and exploit the inherent analogical reasoning rules instead of object similarity. Lastly, the Squeeze-and-Excitation Channel-wise Attention (SECA) in the proposed PredAI discriminates essential attributes and analogies from irrelevant ones. Extensive experiments over four benchmark RPM datasets show that the proposed HP^2AI achieves significant performance gains over all the state-of-the-art methods consistently on all four datasets.

Multimodal sentiment analysis (MSA) aims to integrate multiple modalities of information to better understand human sentiment. The current research mainly focuses on conducting multimodal fusion, which neglects the under-optimized modal representations generated by the imbalance of unimodal performances in joint learning. Moreover, the size of labeled datasets limits the generalization ability of existing supervised models. To address the above issues, this paper proposes a knowledge-enhanced self-supervised balanced representation approach (KEBR). First, a text-based cross-modal fusion method (TCMF) is constructed, which injects the non-verbal information from the videos into the semantic representation of text to enhance the multimodal representation of text. Then, a multimodal cosine constrained loss (MCC) is designed to constrain the fusion of non-verbal information in joint learning to balance the representation. Finally, with the help of sentiment knowledge and non-verbal information, KEBR conducts sentiment word masking and sentiment intensity prediction. Experimental results show that KEBR outperforms the baseline.

Recent years have seen an increase in the use of gigapixel-level image and video capture systems and benchmarks with high-resolution wide (HRW) shots. However, unlike close-up shots in the MS COCO dataset, the higher resolution and wider field of view raise unique challenges, such as extreme sparsity and huge scale changes, causing existing close-up detectors inaccuracy and inefficiency. In this paper, we present a novel model-agnostic sparse vision transformer, dubbed SparseFormer, to bridge the gap of object detection between close-up and HRW shots. The proposed SparseFormer selectively uses attentive tokens to scrutinize the sparsely distributed windows that may contain objects. In this way, it can jointly explore global and local attention by fusing coarse- and fine-grained features to handle huge scale changes. SparseFormer also benefits from a novel Cross-slice non-maximum suppression (C-NMS) algorithm to precisely localize objects from noisy windows and a simple yet effective multi-scale strategy to improve accuracy. Extensive experiments on two HRW benchmarks, PANDA and DOTA-v1.0, demonstrate that the proposed SparseFormer significantly improves detection accuracy (up to 5.8%) and speed (up to 3x) over the state-of-the-art approaches.

Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks even under a black-box setting where the adversary can only query the model. Particularly, query-based black-box adversarial attacks estimate adversarial gradients based on the returned probability vectors of the target model for a sequence of queries. During this process, the queries made to the target model are intermediate adversarial examples crafted at the previous attack step, which share high similarities in the pixel space. Motivated by this observation, stateful detection methods have been proposed to detect and reject query-based attacks. While demonstrating promising results, these methods either have been evaded by more advanced attacks or suffer from low efficiency in terms of the number of shots (queries) required to detect different attacks. Arguably, the key challenge here is to assign high similarity scores for any two intermediate adversarial examples perturbed from the same clean image. To address this challenge, we propose a novel Adversarial Contrastive Prompt Tuning (ACPT) method to robustly fine-tune the CLIP image encoder to extract similar embeddings for any two intermediate adversarial queries. With ACPT, we further introduce a detection framework AdvQDet that can detect 7 state-of-the-art query-based attacks with $>99\%$ detection rate within 5 shots. We also show that ACPT is robust to 3 types of adaptive attacks. Code is available at https://github.com/xinwong/AdvQDet.

Contrastive vision-language pre-training has shown great promise in representation transfer learning and cross-modality learning in the medical field. However, without fully exploiting the intrinsic properties and correlations of multimodal medical data within patient studies, current research fails to explore all the potential of available data, leading to suboptimal performance on representation learning. In this paper, we propose a novel pre-training framework for learning better medical vision-language embedding, oriented on patients' study-level data. Based on the order-agnostic property of radiology report, we adopt a two-stage feature extraction method for more representative textual characterization. Then, by leveraging momentum encoders and memory queues, study-level semantics are explored with three contrastive objectives to provide comprehensive supervision from three perspectives, i.e., cross-modal, multi-modal, and uni-modal, such that the potential information neglected by previous research can be fully exploited. The superiority of the proposed framework is demonstrated by the impressive improvements on four typical downstream tasks, including zero-shot/data-efficient image classification, image segmentation, and cross-modal retrieval.

Despite having tremendous progress in image-to-3D generation, existing methods still struggle to produce multi-view consistent images with high-resolution textures in detail, especially in the paradigm of 2D diffusion that lacks 3D awareness. In this work, we present High-resolution Image-to-3D model (Hi3D), a new video diffusion based paradigm that redefines a single image to multi-view images as 3D-aware sequential image generation (i.e., orbital video generation). This methodology delves into the underlying temporal consistency knowledge in video diffusion model that generalizes well to geometry consistency across multiple views in 3D generation. Technically, Hi3D first empowers the pre-trained video diffusion model with 3D-aware prior (camera pose condition), yielding multi-view images with low-resolution texture details. A 3D-aware video-to-video refiner is learnt to further scale up the multi-view images with high-resolution texture details. Such high-resolution multi-view images are further augmented with novel views through 3D Gaussian Splatting, which are finally leveraged to obtain high-fidelity meshes via 3D reconstruction. Extensive experiments on both novel view synthesis and single view reconstruction demonstrate that our Hi3D manages to produce superior multi-view consistency images with highly-detailed textures. Source code and data are available at https://github.com/yanghb22-fdu/Hi3D-Official.

Neural implicit representations have recently revolutionized simultaneous localization and mapping (SLAM), giving rise to a groundbreaking paradigm known as NeRF-based SLAM. However, existing methods often fall short in accurately estimating poses and reconstructing scenes. This limitation largely stems from their reliance on volume rendering techniques, which oversimplify the modeling process. In this paper, we introduce a novel neural implicit SLAM system named SAR-SLAM to address these shortcomings. Our approach reconstructs Neural Radiance Fields (NeRFs) using a self-attentive architecture and represents scenes through neural point cloud encoding. Unlike previous NeRF-based SLAM methods, which depend on traditional volume rendering equations for scene representation and view synthesis, our method employs a self-attentive rendering framework with the Transformer architecture during mapping and tracking stages. To enable incremental mapping, we anchor scene features within a neural point cloud, striking a balance between estimation accuracy and computational cost. Experimental results on three challenging datasets show the superior performance and robustness of our SAR-SLAM compared to recent NeRF-based SLAM systems. The code will be released.

Scene synthesis has gained significant attention recently, and interactive scene synthesis focuses on yielding scenes according to user preferences. Existing literature either generates floor plans or scenes according to the floor plans. The system proposed in this paper generates scenes over floor plans in real-time. Given an initial scene, the only interaction a user needs is changing the room shapes. Our framework splits/merges rooms and adds/rearranges/removes objects for each transient moment during interactions. A systematic pipeline achieves our framework by compressing objects' arrangements over modified room shapes in a transient moment, thus enabling real-time performances. We also propose elastic boxes that indicate how objects should be arranged according to their continuously changed contexts, such as room shapes and other objects. Through a few interactions, a floor plan filled with object layouts is generated concerning user preferences on floor plans and object layouts according to floor plans. Experiments show that our framework is efficient at user interactions and plausible for synthesizing 3D scenes.

Single Image Super-Resolution (SISR) is a pivotal challenge in computer vision, aiming to restore high-resolution (HR) images from their low-resolution (LR) counterparts. The presence of diverse degradation kernels creates a significant domain gap, limiting the effective generalization of models in real-world scenarios. This study introduces the Bézier Curve basis-based Sparse Coding Network (BCSCN), a preprocessing network designed to mitigate input distribution discrepancies between the training and testing phases of super-resolution networks. BCSCN achieves this by removing visual defects associated with the degradation kernel in LR images, such as artifacts, residual structures, and noise. Additionally, we propose a set of rewards to guide the search for basis coefficients in BCSCN, enhancing the preservation of main content while eliminating information related to degradation. The experimental results highlight the importance of BCSCN, showcasing its capacity to effectively reduce domain gaps and enhance the generalization of super-resolution networks.

The recognition of named entities in visually-rich documents (VrD-NER) plays a critical role in various real-world scenarios and applications. However, the research in VrD-NER faces three major challenges: complex document layouts, incorrect reading orders, and unsuitable task formulations. To address these challenges, we propose a query-aware entity extraction head, namely UNER, to collaborate with existing multi-modal document transformers to develop more robust VrD-NER models. The UNER head considers the VrD-NER task as a combination of sequence labeling and reading order prediction, effectively addressing the issues of discontinuous entities in documents. Experimental evaluations on diverse datasets demonstrate the effectiveness of UNER in improving entity extraction performance. Moreover, the UNER head enables a supervised pre-training stage on various VrD-NER datasets to enhance the document transformer backbones and exhibits substantial knowledge transfer from the pre-training stage to the fine-tuning stage. By incorporating universal layout understanding, a pre-trained UNER-based model demonstrates significant advantages in few-shot and cross-linguistic scenarios and exhibits zero-shot entity extraction abilities.

Few-Shot Industrial Anomaly Detection (FS-IAD) has drawn great attention most recently since data efficiency and the ability to design algorithms for fast migration across products have become the main concerns. The difficulty of memory-based IAD in low-data regime primarily lies in inefficient measurement between the memory bank and query images. We address such a pivotal issue from a new perspective of optimal matching between features of image regions. Taking the unbalanced nature of query features into consideration, we adopt Conditional Transport (CT) as a metric to compute the structural distance between representations of the two sets to determine feature relevance. CT distance generates the optimal matching flows between unbalanced structural elements that achieve the minimum matching cost, which can be directly used for IAD since it well reflects the differences of query images compared with the normal memory. Realizing the fact that query images usually come one-by-one or batch-by-batch, we further propose an Online Conditional Transport (OCT) by making full use of the current and historical query images for IAD via simultaneously calibrating the memory bank using the online query images and matching features between the calibrated memory and the current query image. Go one step further, for sparse foreground products, we employ a predominant segment model to implement Foreground-aware OCT (FOCT) for improving the effectiveness and efficiency of OCT by forcing the model to pay more attention to diverse targets rather than redundant backgrounds when calibrating the memory bank. FOCT can improve the diversity of calibrated memory, which is critical for robust FS-IAD in practice. Besides, FOCT is flexible since it can be friendly plugged and played with any pre-trained backbones, such as WRN, and any pre-trained segment models, such as SAM. The effectiveness and efficiency of our model is demonstrated across diverse datasets, including benchmarks of MVTec and MPDD, achieving SOTA performance.