ECCV 2024 Papers

"In this paper, we address the challenge of fine-grained video event understanding in traffic scenarios, vital for autonomous driving and safety. Traditional datasets focus on driver or vehicle behavior, often neglecting pedestrian perspectives. To fill this gap, we introduce the WTS dataset, highlighting detailed behaviors of both vehicles and pedestrians across over 1.2k video events in over hundreds traffic scenarios. WTS integrates diverse perspectives from vehicle ego and fixed overhead cameras in a vehicle-infrastructure cooperative environment, enriched with comprehensive textual descriptions and unique 3D Gaze data for a synchronized 2D/3D view, focusing on pedestrian analysis. We also provide annotations for 5k publicly sourced pedestrian-related traffic videos. Additionally, we introduce LLMScorer, an LLM-based evaluation metric to align inference captions with ground truth. Using WTS, we establish a benchmark for dense video-to-text tasks, exploring state-of-the-art Vision-Language Models with an instance-aware VideoLLM method as a baseline. WTS aims to advance fine-grained video event understanding, enhancing traffic safety and autonomous driving development. Dataset page: https://woven-visionai.github.io/ wts-dataset-homepage/."

"Whole slide imaging is routinely adopted for carcinoma diagnosis and prognosis. Abundant experience is required for pathologists to achieve accurate and reliable diagnostic results of whole slide images (WSI). The huge size and heterogeneous features of WSIs make the workflow of pathological reading extremely time-consuming. In this paper, we propose a novel framework (WSI-VQA) to interpret WSIs by generative visual question answering. WSI-VQA shows universality by reframing various kinds of slide-level tasks in a question-answering pattern, in which pathologists can achieve immunohistochemical grading, survival prediction, and tumor subtyping following human-machine interaction. Furthermore, we establish a WSI-VQA dataset which contains 8672 slide-level question-answering pairs with 977 WSIs. Besides the ability to deal with different slide-level tasks, our generative model which is named Wsi2Text Transformer (W2T) outperforms existing discriminative models in medical correctness, which reveals the potential of our model to be applied in the clinical scenario. Additionally, we also visualize the co-attention mapping between word embeddings and WSIs as an intuitive explanation for diagnostic results. The dataset and related code are available at https://github.com/cpystan/WSI-VQA."

"For the visible-infrared person re-identification (VI-ReID) task, one of the primary challenges lies in significant cross-modality discrepancy. Existing methods struggle to conduct modality-invariant information mining. They often focus solely on mining singular dimensions like spatial or channel, and overlook the extraction of specific-modality multi-dimension information. To fully mine modality-invariant information across a wide range, we introduce the Wide-Ranging Information Mining Network (WRIM-Net), which mainly comprises a Multi-dimension Interactive Information Mining (MIIM) module and an Auxiliary-Information-based Contrastive Learning (AICL) approach. Empowered by the proposed Global Region Interaction (GRI), MIIM comprehensively mines non-local spatial and channel information through intra-dimension interaction. Moreover, Thanks to the low computational complexity design, separate MIIM can be positioned in shallow layers, enabling the network to better mine specific-modality multi-dimension information. AICL, by introducing the novel Cross-Modality Key-Instance Contrastive (CMKIC) loss, effectively guides the network in extracting modality-invariant information. We conduct extensive experiments not only on the well-known SYSU-MM01 and RegDB datasets but also on the latest large-scale cross-modality LLCM dataset. The results demonstrate WRIM-Net’s superiority over state-of-the-art methods."

"Segmenting and recognizing diverse object parts is crucial in computer vision and robotics. Despite significant progress in object segmentation, part-level segmentation remains underexplored due to complex boundaries and scarce annotated data. To address this, we propose a novel Weakly-supervised Part Segmentation (WPS) setting and an approach called WPS-SAM, built on the large-scale pre-trained vision foundation model, Segment Anything Model (SAM). WPS-SAM is an end-to-end framework designed to extract prompt tokens directly from images and perform pixel-level segmentation of part regions. During its training phase, it only uses weakly supervised labels in the form of bounding boxes or points. Extensive experiments demonstrate that, through exploiting the rich knowledge embedded in pre-trained foundation models, WPS-SAM outperforms other segmentation models trained with pixel-level strong annotations. Specifically, WPS-SAM achieves 68.93% mIOU and 79.53% mACC on the PartImageNet dataset, surpassing state-of-the-art fully supervised methods by approximately 4% in terms of mIOU."

"Estimating human and camera trajectories with accurate scale in the world coordinate system from a monocular video is a highly desirable yet challenging and ill-posed problem. In this study, we aim to recover expressive parametric human models (, SMPL-X) and corresponding camera poses jointly, by leveraging the synergy between three critical players: the world, the human, and the camera. Our approach is founded on two key observations. Firstly, camera-frame SMPL-X estimation methods readily recover absolute human depth. Secondly, human motions inherently provide absolute spatial cues. By integrating these insights, we introduce a novel framework, referred to as , to facilitate world-grounded expressive human pose and shape estimation (EHPS) alongside camera pose estimation, without relying on traditional optimization techniques. Additionally, we present a new synthetic dataset, , which includes accurately annotated humans and cameras, and features diverse interactive human motions as well as realistic camera trajectories. Extensive experiments on both standard and newly established benchmarks highlight the superiority and efficacy of our framework. The code and dataset are available on the homepage1 . 1 Homepage: https://wqyin.github.io/projects/WHAC/."

"Training from pre-trained models (PTM) is a popular approach for fast machine learning (ML) service deployment. Recent studies on hardware security have revealed that ML systems could be compromised through flipping bits in model parameters (e.g., weights) with memory faults. In this paper, we introduce (i.e., weight bit poisoning), a novel task-agnostic backdoor attack that manifests during the victim’s training time (i.e., fine-tuning from a public and clean PTM) by inducing hardware-based weight bit flips. utilizes a novel distance-aware algorithm that identifies bit flips to maximize the distance between the distribution of poisoned output representations (ORs) and clean ORs based on the public PTM. This unique set of bit flips can be applied to backdoor any victim model during the fine-tuning of the same public PTM, regardless of the downstream tasks. We evaluate on state-of-the-art CNNs and Vision Transformer models with representative downstream tasks. The results show that can compromise a wide range of PTMs and downstream tasks with an average 99.3% attack success rate by flipping as few as 11 model weight bits. can be effective in various training configurations with respect to learning rate, optimizer, and fine-tuning duration. We investigate limitations of existing backdoor protection techniques against and discuss potential future mitigation. 1 1 Our code can be accessed at: https://github.com/casrl/WBP"

"Text-driven video editing has emerged as a prominent application based on the breakthroughs of image diffusion models. Existing state-of-the-art methods focus on zero-shot frameworks due to limited training data and computing resources. To preserve structure consistency, previous frameworks usually employ Denoising Diffusion Implicit Model (DDIM) inversion to provide inverted noise latents as guidance. The key challenge lies in limiting errors caused by the randomness and inaccuracy in each step of the naı̈ve DDIM inversion process, which can lead to temporal inconsistency in video editing tasks. Our observation indicates that incorporating temporal keyframe information can alleviate the accumulated error during inversion. In this paper, we propose an effective warping strategy in the feature domain to obtain high-quality DDIM inverted noise latents. Specifically, we shuffle the editing frames randomly in each timestep and use optical flow extracted from the source video to propagate the latent features of the first keyframe to subsequent keyframes. Moreover, we develop a comprehensive zero-shot framework that adapts to this strategy in both the inversion and denoising processes, thereby facilitating the generation of consistent edited videos. We compare our method with state-of-the-art text-driven editing methods on various real-world videos with different forms of motion. The project page is available at https://ree1s.github.io/wave/."

"Accurate text segmentation results are crucial for text-related generative tasks, such as text image generation, text editing, text removal, and text style transfer. Recently, some scene text segmentation methods have made significant progress in segmenting regular text. However, these methods perform poorly in scenarios containing artistic text. Therefore, this paper focuses on the more challenging task of artistic text segmentation and constructs a real artistic text segmentation dataset. One challenge of the task is that the local stroke shapes of artistic text are changeable with diversity and complexity. We propose a decoder with the layer-wise momentum query to prevent the model from ignoring stroke regions of special shapes. Another challenge is the complexity of the global topological structure. We further design a skeleton-assisted head to guide the model to focus on the global structure. Additionally, to enhance the generalization performance of the text segmentation model, we propose a strategy for training data synthesis, based on the large multi-modal model and the diffusion model. Experimental results show that our proposed method and synthetic dataset can significantly enhance the performance of artistic text segmentation and achieve state-of-the-art results on other public datasets. The datasets and codes are available at: https://github.com/xdxie/WAS WordArt-Segmentation."

"We propose a novel Neural Radiance Field (NeRF) representation for non-opaque scenes that enables fast inference by utilizing textured polygons. Despite the high-quality novel view rendering that NeRF provides, a critical limitation is that it relies on volume rendering that can be computationally expensive and does not utilize the advancements in modern graphics hardware. Many existing methods fall short when it comes to modelling volumetric effects as they rely purely on surface rendering. We thus propose to model the scene with polygons, which can then be used to obtain the quadrature points required to model volumetric effects, and also their opacity and colour from the texture. To obtain such polygonal mesh, we train a specialized field whose zero-crossings would correspond to the quadrature points when volume rendering, and perform marching cubes on this field. We then perform ray-tracing and utilize the ray-tracing shader to obtain the final colour image. Our method allows an easy integration with existing graphics frameworks allowing rendering speed of over 100 frames-per-second for a 1920 × 1080 image, while still being able to represent non-opaque objects."

"This paper presents Invariant Score Distillation (ISD), a novel method for high-fidelity text-to-3D generation. ISD aims to tackle the over-saturation and over-smoothing problems in Score Distillation Sampling (SDS). In this paper, SDS is decoupled into a weighted sum of two components: the reconstruction term and the classifier-free guidance term. We experimentally found that over-saturation stems from the large classifier-free guidance scale and over-smoothing comes from the reconstruction term. To overcome these problems, ISD utilizes an invariant score term derived from DDIM sampling to replace the reconstruction term in SDS. This operation allows the utilization of a medium classifier-free guidance scale and mitigates the reconstruction-related errors, thus preventing the over-smoothing and over-saturation of results. Extensive experiments demonstrate that our method greatly enhances SDS and produces realistic 3D objects through single-stage optimization."

"Recently, with the rapid advancements of generative models, the field of visual text generation has witnessed significant progress. However, it is still challenging to render high-quality text images in real-world scenarios, as three critical criteria should be satisfied: (1) Fidelity: the generated text images should be photo-realistic and the contents are expected to be the same as specified in the given conditions; (2) Reasonability: the regions and contents of the generated text should cohere with the scene; (3) Utility: the generated text images can facilitate related tasks (, text detection and recognition). Upon investigation, we find that existing methods, either rendering-based or diffusion-based, can hardly meet all these aspects simultaneously, limiting their application range. Therefore, we propose in this paper a visual text generator (termed SceneVTG), which can produce high-quality text images in the wild. Following a two-stage paradigm, SceneVTG leverages a Multimodal Large Language Model to recommend reasonable text regions and contents across multiple scales and levels, which are used by a conditional diffusion model as conditions to generate text images. Extensive experiments demonstrate that the proposed SceneVTG significantly outperforms traditional rendering-based methods and recent diffusion-based methods in terms of fidelity and reasonability. Besides, the generated images provide superior utility for tasks involving text detection and text recognition. Code and datasets are available at magentaAdvancedLiterateMachinery."

"What will be the relationships between objects in a novel view? We strive to answer this question by investigating a new visual cognition task, termed visual relationship transformation or VRT. Unlike prior visual relationship detection task that works on visible view images, VRT aims to predict the relationships in unseen novel views from a single observed source view. Towards solving VRT, we propose an end-to-end deep approach that, given an observed view image and inter-view transformations, learns to predict the relationships in novel views. Specifically, we introduce an equivariant graph neural network to predict the relationships between objects in novel views, which is achieved by enforcing the transformation equivariance of the learned relationship representations. Simultaneously, a relationship presentness mask is learned for pruning the invisible ones, thus enabling the visible relationship prediction in novel views. To this end, VRT provides supplementary cues for accomplishing novel-view-related tasks, such as visual grounding (VG), novel view synthesis (NVS), and pedestrian intention estimation (PIE). In the experiments, adopting VRT as a plug-in module results in considerable performance improvements in VG, NVS, and PIE across all datasets."

"Visual prompts represent a lightweight approach that adapts pre-trained models to downstream tasks without modifying the model parameters. They strategically transform the input and output through prompt engineering and label mapping, respectively. Yet, existing methodologies often overlook the synergy between these components, leaving the intricate relationship between them underexplored. To address this, we propose an Optimal Transport-based Label Mapping strategy (OTLM) that effectively reduces distribution migration and lessens the modifications required by the visual prompts. Specifically, we reconceptualize label mapping as a partial optimal transport problem, and introduce a novel transport cost matrix. Through the optimal transport framework, we establish a connection between output-side label mapping and input-side visual prompting. Additionally, we analyze frequency-based label mapping methods within this framework. We also offer an analysis of frequency-based label mapping techniques and demonstrate the superiority of our OTLM method. Our experiments across multiple datasets and various model architectures demonstrate significant performance improvements, which prove the effectiveness of the proposed method."

"Generalization is a pivotal challenge for agents following natural language instructions. To approach this goal, we leverage a vision-language model (VLM) for visual grounding and transfer its vision-language knowledge into reinforcement learning (RL) for object-centric tasks, which makes the agent capable of zero-shot generalization to unseen objects and instructions. By visual grounding, we obtain an object-grounded confidence map for the target object indicated in the instruction. Based on this map, we introduce two routes to transfer VLM knowledge into RL. Firstly, we propose an object-grounded intrinsic reward function derived from the confidence map to more effectively guide the agent towards the target object. Secondly, the confidence map offers a more unified, accessible task representation for the agent’s policy, compared to language embeddings. This enables the agent to process unseen objects and instructions through comprehensible visual confidence maps, facilitating zero-shot object-level generalization. Single-task experiments prove that our intrinsic reward significantly improves performance on challenging skill learning. In multi-task experiments, through testing on tasks beyond the training set, we show that the agent, when provided with the confidence map as the task representation, possesses better generalization capabilities than language-based conditioning. The code is available at https://github.com/PKU-RL/COPL."

"Sign Language Translation (SLT) aims to translate sign videos into text sentences. While gloss sequences, the written approximation of sign videos, provide informative alignment supervision for visual representation learning in SLT, the associated high cost of gloss annotations hampers the scalability. Recent works have yet to achieve satisfactory results without gloss annotations. In this study, we attribute the challenge to the flexible correspondence between visual and textual tokens, and aim to address it by constructing a gloss-like constraint from text sentences. Specifically, we propose a Visual Alignment Pre-training (VAP) scheme to exploit visual information by aligning visual and textual tokens in a greedy manner. The VAP scheme enhances visual encoder in capturing semantic-aware visual information and facilitates better adaptation with translation modules pre-trained on large-scale corpora. Experimental results across four SLT benchmarks demonstrate the effectiveness of VAP, which can generate reasonable alignments and significantly narrow the performance gap with gloss-based methods."

"We embark on the age-old quest: unveiling the hidden dimensions of objects from mere glimpses of their visible parts. To address this, we present Vista3D, a framework that realizes swift and consistent 3D generation within a mere 5 minutes. At the heart of Vista3D lies a two-phase approach: the coarse phase and the fine phase. In the coarse phase, we rapidly generate initial geometry with Gaussian Splatting from a single image. In the fine phase, we extract a Signed Distance Function (SDF) directly from learned Gaussian Splatting, optimizing it with a differentiable isosurface representation. Furthermore, it elevates the quality of generation by using a disentangled representation with two independent implicit functions to capture both visible and obscured aspects of objects. Additionally, it harmonizes gradients from 2D diffusion prior with 3D-aware diffusion priors by angular diffusion prior composition. Through extensive evaluation, we demonstrate that Vista3D effectively sustains a balance between the consistency and diversity of the generated 3D objects. Demos and code will be available at https://github.com/florinshen/Vista3D."

"Predicting future trajectories for other road agents is an essential task for autonomous vehicles. Established trajectory prediction methods primarily use agent tracks generated by a detection and tracking system and HD map as inputs. In this work, we propose a novel method that also incorporates visual input from surround-view cameras, allowing the model to utilize visual cues such as human gazes and gestures, road conditions, vehicle turn signals, etc, which are typically hidden from the model in prior methods. Furthermore, we use textual descriptions generated by a Vision-Language Model (VLM) and refined by a Large Language Model (LLM) as supervision during training to guide the model on what to learn from the input data. Despite using these extra inputs, our method achieves a latency of 53 ms, making it feasible for real-time processing, which is significantly faster than that of previous single-agent prediction methods with similar performance. Our experiments show that both the visual inputs and the textual descriptions contribute to improvements in trajectory prediction performance, and our qualitative analysis highlights how the model is able to exploit these additional inputs. Lastly, in this work we create and release the nuScenes-Text dataset, which augments the established nuScenes dataset with rich textual annotations for every scene, demonstrating the positive impact of utilizing VLM on trajectory prediction. Our project page is at https://moonseokha.github.io/VisionTrap."

"We all know that large language models are built on top of a transformer-based architecture to process textual inputs. For example, the LLaMA family of models stands out among many open-source implementations. Can the same transformer be used to process 2D images? In this paper, we answer this question by unveiling a LLaMA-like vision transformer in plain and pyramid forms, termed , which is tailored for this purpose. is a unified and generic modeling framework for solving most vision tasks. We extensively evaluate its effectiveness using typical pre-training paradigms in a good portion of downstream tasks of image perception and especially image generation. In many cases, has exhibited substantial gains over the previous state-of-the-art vision transformers. It is our hope that researchers in computer vision can apply presented here to solve various specific image generation and perception tasks. Code is at: https://github.com/Meituan-AutoML/VisionLLaMA"

"Out-of-distribution (OOD) detection is a significant challenge in deploying pattern recognition and machine learning models, as models often fail on data from novel distributions. Recent vision-language models (VLMs) such as CLIP have shown promise in OOD detection through their generalizable multimodal representations. Existing CLIP-based OOD detection methods only utilize a single modality of in-distribution (ID) information (, textual cues). However, we find that the ID visual information helps to leverage CLIP’s full potential for OOD detection. In this paper, we pursue a different approach and explore the regime to leverage both the visual and textual ID information. Specifically, we propose Dual-Pattern Matching (DPM), efficiently adapting CLIP for OOD detection by leveraging both textual and visual ID patterns. DPM stores ID class-wise text features as the textual pattern and the aggregated ID visual information as the visual pattern. At test time, the similarity to both patterns is computed to detect OOD inputs. We further extend DPM with lightweight adaptation for enhanced OOD detection. Experiments demonstrate DPM’s advantages, outperforming existing methods on common benchmarks. The dual-pattern approach provides a simple yet effective way to exploit multi-modality for OOD detection with vision-language representations."