The frame quality deterioration problem is one of the main challenges in the field of video understanding. To compensate for the information loss caused by deteriorated frames, recent approaches exploit transformer-based integration modules to obtain spatio-temporal information. However, these integration modules are heavy and complex. Furthermore, each integration module is specifically tailored for its target task, making it difficult to generalise to multiple tasks. In this paper, we present a neat and unified framework, called Spatio-Temporal Prompting Network (STPN). It can efficiently extract robust and accurate video features by dynamically adjusting the input features in the backbone network. Specifically, STPN predicts several video prompts containing spatio-temporal information of neighbour frames. Then, these video prompts are prepended to the patch embeddings of the current frame as the updated input for video feature extraction. Moreover, STPN is easy to generalise to various video tasks because it does not contain task-specific modules. Without bells and whistles, STPN achieves state-of-the-art performance on three widely-used datasets for different video understanding tasks, i.e., ImageNetVID for video object detection, YouTubeVIS for video instance segmentation, and GOT-10k for visual object tracking. Codes are available at https://github.com/guanxiongsun/STPN.
论文检索
输入标题、作者或关键词，从 5,999 篇学术成果中精准定位
We propose a novel framework for interactive class-agnostic object counting, where a human user can interactively provide feedback to improve the accuracy of a counter. Our framework consists of two main components: a user-friendly visualizer to gather feedback and an efficient mechanism to incorporate it. In each iteration, we produce a density map to show the current prediction result, and we segment it into non-overlapping regions with an easily verifiable number of objects. The user can provide feedback by selecting a region with obvious counting errors and specifying the range for the estimated number of objects within it. To improve the counting result, we develop a novel adaptation loss to force the visual counter to output the predicted count within the user-specified range. For effective and efficient adaptation, we propose a refinement module that can be used with any density-based visual counter, and only the parameters in the refinement module will be updated during adaptation. Our experiments on two challenging class-agnostic object counting benchmarks, FSCD-LVIS and FSC-147, show that our method can reduce the mean absolute error of multiple state-of-the-art visual counters by roughly 30% to 40% with minimal user input. Our project can be found at https://yifehuang97.github.io/ICACountProjectPage/.
Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that instead of hinging on these strenuous operations, quality image representations can be learned by treating scene/multi-label image SSL simply as a multi-label classification problem, which greatly simplifies the learning framework. Specifically, multiple binary pseudo-labels are assigned for each input image by comparing its embeddings with those in two dictionaries, and the network is optimized using the binary cross entropy loss. The proposed method is named Multi-Label Self-supervised learning (MLS). Visualizations qualitatively show that clearly the pseudo-labels by MLS can automatically find semantically similar pseudo-positive pairs across different images to facilitate contrastive learning. MLS learns high quality representations on MS-COCO and achieves state-of-the-art results on classification, detection and segmentation benchmarks. At the same time, MLS is much simpler than existing methods, making it easier to deploy and for further exploration.
When handling complicated text images (e.g., irregular structures, low resolution, heavy occlusion, and uneven illumination), existing supervised text recognition methods are data-hungry. Although these methods employ large-scale synthetic text images to reduce the dependence on annotated real images, the domain gap still limits the recognition performance. Therefore, exploring the robust text feature representations on unlabeled real images by self-supervised learning is a good solution. However, existing self-supervised text recognition methods conduct sequence-to-sequence representation learning by roughly splitting the visual features along the horizontal axis, which limits the flexibility of the augmentations, as large geometric-based augmentations may lead to sequence-to-sequence feature inconsistency. Motivated by this, we propose a novel self-supervised Character-to-Character Distillation method, CCD, which enables versatile augmentations to facilitate general text representation learning. Specifically, we delineate the character structures of unlabeled real images by designing a self-supervised character segmentation module. Following this, CCD easily enriches the diversity of local characters while keeping their pairwise alignment under flexible augmentations, using the transformation matrix between two augmented views from images. Experiments demonstrate that CCD achieves state-of-the-art results, with average performance gains of 1.38% in text recognition, 1.7% in text segmentation, 0.24 dB (PSNR) and 0.0321 (SSIM) in text super-resolution. Code will be released soon.
From video, we reconstruct a neural volume that captures time-varying color, density, scene flow, semantics, and attention information. The semantics and attention let us identify salient foreground objects separately from the background across spacetime. To mitigate low resolution semantic and attention features, we compute pyramids that trade detail with whole-image context. After optimization, we perform a saliency-aware clustering to decompose the scene. To evaluate real-world scenes, we annotate object masks in the NVIDIA Dynamic Scene and DyCheck datasets. We demonstrate that this method can decompose dynamic scenes in an unsupervised way with competitive performance to a supervised method, and that it improves foreground/background segmentation over recent static/dynamic split methods. Project webpage: https://visual.cs.brown.edu/saff
Panoptic Scene Graph has recently been proposed for comprehensive scene understanding. However, previous works adopt a fully-supervised learning manner, requiring large amounts of pixel-wise densely-annotated data, which is always tedious and expensive to obtain. To address this limitation, we study a new problem of Panoptic Scene Graph Generation from Purely Textual Descriptions (Caption-to-PSG). The key idea is to leverage the large collection of free image-caption data on the Web alone to generate panoptic scene graphs. The problem is very challenging for three constraints: 1) no location priors; 2) no explicit links between visual regions and textual entities; and 3) no pre-defined concept sets. To tackle this problem, we propose a new framework TextPSG consisting of four modules, i.e., a region grouper, an entity grounder, a segment merger, and a label generator, with several novel techniques. The region grouper first groups image pixels into different segments and the entity grounder then aligns visual segments with language entities based on the textual description of the segment being referred to. The grounding results can thus serve as pseudo labels enabling the segment merger to learn the segment similarity as well as guiding the label generator to learn object semantics and relation predicates, resulting in a fine-grained structured scene understanding. Our framework is effective, significantly outperforming the baselines and achieving strong out-of-distribution robustness. We perform comprehensive ablation studies to corroborate the effectiveness of our design choices and provide an in-depth analysis to highlight future directions. Our code, data, and results are available on our project page: https://vis-www.cs.umass.edu/TextPSG.
Most model-free visual object tracking methods formulate the tracking task as object location estimation given by a 2D segmentation or a bounding box in each video frame. We argue that this representation is limited and instead propose to guide and improve 2D tracking with an explicit object representation, namely the textured 3D shape and 6DoF pose in each video frame. Our representation tackles a complex long-term dense correspondence problem between all 3D points on the object for all video frames, including frames where some points are invisible. To achieve that, the estimation is driven by re-rendering the input video frames as well as possible through differentiable rendering, which has not been used for tracking before. The proposed optimization minimizes a novel loss function to estimate the best 3D shape, texture, and 6DoF pose. We improve the state-of-the-art in 2D segmentation tracking on three different datasets with mostly rigid objects.
Pseudo-labeling is significant for semi-supervised instance segmentation, which generates instance masks and classes from unannotated images for subsequent training. However, in existing pipelines, pseudo-labels that contain valuable information may be directly filtered out due to mismatches in class and mask quality. To address this issue, we propose a novel framework, called pseudo-label aligning instance segmentation (PAIS), in this paper. In PAIS, we devise a dynamic aligning loss (DALoss) that adjusts the weights of semi-supervised loss terms with varying class and mask score pairs. Through extensive experiments conducted on the COCO and Cityscapes datasets, we demonstrate that PAIS is a promising framework for semi-supervised instance segmentation, particularly in cases where labeled data is severely limited. Notably, with just 1% labeled data, PAIS achieves 21.2 mAP (based on Mask-RCNN) and 19.9 mAP (based on K-Net) on the COCO dataset, outperforming the current state-of-the-art model, i.e., NoisyBoundary with 7.7 mAP, by a margin of over 12 points. Code is available at: https://github.com/hujiecpp/PAIS.
Monocular depth estimation is known as an ill-posed task that objects in a 2D image usually do not contain sufficient information to predict their depth. Thus, it acts differently from other tasks (e.g., classification and segmentation) in many ways. In this paper, we find that self-supervised monocular depth estimation shows a direction sensitivity and environmental dependency in the feature representation. But the current CNN backbones borrowed from other tasks cannot handle different types of environmental information efficiently, limiting the overall depth accuracy. To bridge this gap, we propose a new Direction-aware Cumulative Convolution Network (DaCCN), which improves the depth feature representation in two aspects. First, we propose a direction-aware module, which can learn to adjust the feature extraction in each direction, facilitating the encoding of different types of information. Secondly, we design a new cumulative convolution to improve the efficiency for aggregating important environmental information. Experiments show that our method achieves significant improvements on three widely used benchmarks and sets a new state-of-the-art performance on the popular benchmarks with all three types of self-supervision.
Recent advances in semi-supervised semantic segmentation have been heavily reliant on pseudo labeling to compensate for limited labeled data, disregarding the valuable relational knowledge among semantic concepts. To bridge this gap, we devise LogicDiag, a brand new neural-logic semi-supervised learning framework. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. LogicDiag resolves such conflicts via reasoning with logic-induced diagnoses, enabling the recovery of (potentially) erroneous pseudo labels, ultimately alleviating the notorious error accumulation problem. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules. Extensive experiments on three standard semi-supervised semantic segmentation benchmarks demonstrate the effectiveness and generality of LogicDiag. Moreover, LogicDiag highlights the promising opportunities arising from the systematic integration of symbolic reasoning into the prevalent statistical, neural learning approaches.
Multi-task learning faces two challenging issues: (1) the high cost of annotating labels for all tasks and (2) balancing the training progress of various tasks with different natures. To resolve the label annotation issue, we construct a large-scale "partially annotated" multi-task dataset by combining task-specific datasets. However, the numbers of annotations for individual tasks are imbalanced, which may escalate an imbalance in training progress. To balance the training progress, we propose an achievement-based multi-task loss to modulate training speed based on the "achievement," defined as the ratio of current accuracy to single-task accuracy. Then, we formulate the multitask loss as a weighted geometric mean of individual task losses instead of a weighted sum to prevent any task from dominating the loss. In experiments, we evaluated the accuracy and training speed of the proposed multi-task loss on the large-scale multi-task dataset against recent multitask losses. The proposed loss achieved the best multi-task accuracy without incurring training time overhead. Compared to single-task models, the proposed one achieved 1.28%, 1.65%, and 1.18% accuracy improvement in object detection, semantic segmentation, and depth estimation, respectively, while reducing computations to 33.73%. Source code is available at https://github.com/ samsung/Achievement-based-MTL.
Despite being highly performant, deep neural networks might base their decisions on features that spuriously correlate with the provided labels, thus hurting generalization. To mitigate this, 'model guidance' has recently gained popularity, i.e. the idea of regularizing the models' explanations to ensure that they are "right for the right reasons". While various techniques to achieve such model guidance have been proposed, experimental validation of these approaches has thus far been limited to relatively simple and / or synthetic datasets. To better understand the effectiveness of the various design choices that have been explored in the context of model guidance, in this work we conduct an in-depth evaluation across various loss functions, attribution methods, models, and 'guidance depths' on the PASCAL VOC 2007 and MS COCO 2014 datasets. As annotation costs for model guidance can limit its applicability, we also place a particular focus on efficiency. Specifically, we guide the models via bounding box annotations, which are much cheaper to obtain than the commonly used segmentation masks, and evaluate the robustness of model guidance under limited (e.g. with only 1% of annotated images) or overly coarse annotations. Further, we propose using the EPG score as an additional evaluation metric and loss function ('Energy loss'). We show that optimizing for the Energy loss leads to models that exhibit a distinct focus on object-specific features, despite only using bounding box annotations that also include background regions. Lastly, we show that such model guidance can improve generalization under distribution shifts. Code available at: https://github.com/sukrutrao/Model-Guidance
Large-scale pre-training tasks like image classification, captioning, or self-supervised techniques do not incentivize learning the semantic boundaries of objects. However, recent generative foundation models built using text-based latent diffusion techniques may learn semantic boundaries. This is because they have to synthesize intricate details about all objects in an image based on a text description. Therefore, we present a technique for segmenting real and AI-generated images using latent diffusion models (LDMs) trained on internet-scale datasets. First, we show that the latent space of LDMs (z-space) is a better input representation compared to other feature representations like RGB images or CLIP encodings for text-based image segmentation. By training the segmentation models on the latent z-space, which creates a compressed representation across several domains like different forms of art, cartoons, illustrations, and photographs, we are also able to bridge the domain gap between real and AI-generated images. We show that the internal features of LDMs contain rich semantic information and present a technique in the form of LD-ZNet to further boost the performance of text-based segmentation. Overall, we show up to 6% improvement over standard baselines for text-to-image segmentation on natural images. For AI-generated imagery, we show close to 20% improvement compared to state-of-the-art techniques. The project is available at https://koutilya-pnvr.github.io/LD-ZNet/.
As a mainstream framework in the field of semi-supervised learning (SSL), self-training via pseudo labeling and its variants have witnessed impressive progress in semi-supervised semantic segmentation with the recent advance of deep neural networks. However, modern self-training based SSL algorithms use a pre-defined constant threshold to select unlabeled pixel samples that contribute to the training, thus failing to be compatible with different learning difficulties of variant categories and different learning status of the model. To address these issues, we propose Enhanced Soft Label (ESL), a curriculum learning approach to fully leverage the high-value supervisory signals implicit in the untrustworthy pseudo label. ESL believes that pixels with unconfident predictions can be pretty sure about their belonging to a subset of dominant classes though being arduous to determine the exact one. It thus contains a Dynamic Soft Label (DSL) module to dynamically maintain the high probability classes, keeping the label "soft" so as to make full use of the high entropy prediction. However, the DSL itself will inevitably introduce ambiguity between dominant classes, thus blurring the classification boundary. Therefore, we further propose a pixel-to-part contrastive learning method cooperated with an unsupervised object part grouping mechanism to improve its ability to distinguish between different classes. Extensive experimental results on Pascal VOC 2012 and Cityscapes show that our approach achieves remarkable improvements over existing state-of-the-art approaches.
Semantic segmentation has made significant progress in recent years thanks to deep neural networks, but the common objective of generating a single segmentation output that accurately matches the image's content may not be suitable for safety-critical domains such as medical diagnostics and autonomous driving. Instead, multiple possible correct segmentation maps may be required to reflect the true distribution of annotation maps. In this context, stochastic semantic segmentation methods must learn to predict conditional distributions of labels given the image, but this is challenging due to the typically multimodal distributions, high-dimensional output spaces, and limited annotation data. To address these challenges, we propose a conditional categorical diffusion model (CCDM) for semantic segmentation based on Denoising Diffusion Probabilistic Models. Our model is conditioned to the input image, enabling it to generate multiple segmentation label maps that account for the aleatoric uncertainty arising from divergent ground truth annotations. Our experimental results show that CCDM achieves state-of-the-art performance on LIDC, a stochastic semantic segmentation dataset, and outperforms established baselines on the classical segmentation dataset Cityscapes.
Recent years have witnessed dramatic progress in computer vision technologies and their broad applications, where manufacturing and industrial fields are important branches that highly require computer vision to bring them intelligent updating. As the name suggests, our workshop focus on advanced multimedia computing for smart manufacturing and engineering. We want to collect advances in using computer vision in various applications of smart manufacturing and engineering, theoretical research and practical applications are both welcome. The accepted papers cover the practical applications of advanced multimedia computing in tunnel water leakage recognition and segmentation, multi-class lane detection, gaze estimation, and also the theoretical achievements on spectrum sensing, semantic segmentation, image classification, information security, etc. This workshop goals to boost the concern of the public on exploiting multimedia computing for intelligent manufacturing and engineering.
Human emotion understanding is pivotal in making conversational technology mainstream. We view speech emotion understanding as a perception task which is a more realistic setting. With varying contexts (languages, demographics etc.) different share of people perceive the same speech segment as a non-unanimous emotion. As part of the ACM Multimedia 2023 Computational Paralinguistics ChallengE (ComParE) in the EMotion Share track, we leverage their rich dataset of multilingual speakers and multi-label regression target of 'emotion share' or perception of that emotion. We demonstrate that the training scheme of different foundation models dictates their effectiveness for tasks beyond speech recognition, especially for non-semantic speech tasks like emotion understanding. This is a very complex task due to multilingual speakers, variability in the target labels, and inherent imbalance in the regression dataset. Our results show that HuBERT-Large with a self-attention-based light-weight sequence model provides 4.6% improvement over the reported baseline.
Facial expression spotting holds significant importance as it can signify emotional changes. Particularly, micro-expressions possess the potential to reveal genuine emotions, making them even more valuable in practical domains such as public safety and finance. However, spotting micro-expressions proves challenging due to their subtle movements and brief duration. This paper proposes an expression spotting method based on face alignment and optical flow. We first use a finer crop-align technique to preprocess the facial videos by aligning the face and the nose tip. Then, regions of interest (ROIs) are defined by analyzing the statistics of action units. The optical flow features are then extracted and subjected to low-pass filtering to eliminate high-frequency noise. Furthermore, candidate expression segments are identified based on the magnitude of the processed optical flows. Finally, non-maximum suppression is utilized to remove overlapping segments. The effectiveness of the proposed method is evaluated on the challenge test set, resulting in an overall F1-score of 0.19. Additional results obtained from CAS(ME)2 and SAMM Long videos provide further verification of the method's efficacy. The code is available online.
Human-centric visual analysis is a fundamental task for many multimedia and computer vision applications, such as self-driving, multimedia retrieval, and augmented reality, etc. Based on our recent research efforts on fine-grained human visual analysis, we develop a robust and efficient human-centric visual analysis system named as HumVis. HumVis is built on a simple yet efficient contextual instance decoupling (CID) module, which can effectively separate different persons in an input image and output corresponding person structure information for visual analysis. Based on CID, HumVis achieves accurate multi-person pose estimation, multi-person foreground segmentation, multi-person part segmentation and 3D human mesh recovery for user-uploaded images/videos and support live stream presentation.
We propose a system to generate 360° realistic virtual worlds (360RVW) for the interactive spatial exploration of omnidirectional street-view videos. Our 360RVW enables users to explore photorealistic scenes with digital avatars, and interact with others. To create the virtual worlds our system only requires 360° videos with annotations of the start and end camera coordinate as input. We first detect street intersections to divide the input videos and remove the camera operator from the recordings using a video completion technique. Next, we analyze the 3D structure of the scene using semantic segmentation to define walkable areas. Finally, we render the environment using an ellipsoid projection surface to achieve a more realistic integration of the avatar into real-world 360° videos. The whole process is largely automated, enabling users to produce realistic and interactive virtual worlds without specialized skills or time-consuming manual interventions.