Most current pipelines for spatiotemporal action localization connect frame-wise or clip-wise detection results to generate action proposals. In this paper, we propose Coarse-to-Fine Action Detector (CFAD), an original end-to-end trainable framework for efficient spatiotemporal action localization. The CFAD introduces a new paradigm that first estimates coarse spatiotemporal action tubes from video streams, and then refines the tubes’ location based on key timestamps. This concept is implemented by two key components, the Coarse and Refine Modules in our frame-work. The parameterized modeling of long temporal information in the Coarse Module helps obtain accurate classification and initial tube estimation, while the Refine Module selectively adjusts the tube location under the guidance of key timestamps. Against other methods, the proposed CFAD achieves state-of-the-art results on action detection bench-marks of UCF101-24, UCFSports and JHMDB-21 with inference speed that is 3.3× faster than the nearest competitor.
论文检索
输入标题、作者或关键词，从 1,358 篇学术成果中精准定位
In this paper, we build upon the weakly-supervised generation mechanism of intermediate attention maps in any convolutional neural networks and disclose the effectiveness of attention modules more straightforwardly to fully exploit their potential. Given an existing neural network equipped with arbitrary attention modules, we introduce a meta critic network to evaluate the quality of attention maps in the main network. Due to the discreteness of our designed reward, the proposed learning method is arranged in a reinforcement learning setting, where the attention actors and recurrent critics are alternately optimized to provide instant critique and revision for the temporary attention representation, hence coined as Deep REinforced Attention Learning (DREAL). It could be applied universally to network architectures with different types of attention modules and promotes their expressive ability by maximizing the relative gain of the final recognition performance arising from each individual attention module, as demonstrated by extensive experiments on both category and instance recognition benchmarks.
Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines. The problem is that viewing angle and distance severely impact the recognizability of a local feature. Attempts to improve appearance invariance by choosing better local feature points or by leveraging outside information, have come with pre-requisites that made some of them impractical. In this paper, we propose a surprisingly effective enhancement to local feature extraction, which improves matching. We show that CNN-based depths inferred from single RGB images, are quite helpful, despite their flaws. They allow us to pre-warp images and rectify perspective distortions, to significantly enhance SIFT and BRISK features, enabling more good matches, even when cameras are looking at the same scene but in opposite directions.
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited. Unlike previous attempts that exploit few-shot classification techniques to facilitate FSOD, this work highlights the necessity of handling the problem of scale variations, which is challenging due to the unique sample distribution. To this end, we propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD. It generates multi-scale positive samples as object pyramids and refines the prediction at various scales. We demonstrate its advantage by integrating it as an auxiliary branch to the popular architecture of Faster R-CNN with FPN, delivering a strong FSOD solution. Several experiments are conducted on PASCAL VOC and MS COCO, and the proposed approach achieves state of the art results and significantly outperforms other counterparts, which shows its effectiveness.
Predictor combination aims to improve a (target) predictor of a learning task based on the (reference) predictors of potentially relevant tasks, without having access to the internals of individual predictors. We present a new predictor combination algorithm that improves the target by i) measuring the relevance of references based on their capabilities in predicting the target, and ii) strengthening such estimated relevance. Unlike existing predictor combination approaches that only exploit pairwise relationships between the target and each reference, and thereby ignore potentially useful dependence among references, our algorithm jointly assesses the relevance of all references by adopting a Bayesian framework. This also offers a rigorous way to automatically select only relevant references. Based on experiments on six real-world datasets from visual attribute ranking and multi-class classification scenarios, we demonstrate that our algorithm offers a significant performance gain and broadens the application range of existing predictor combination approaches.
Open Set Domain Adaptation (OSDA) bridges the domain gap between a labeled source domain and an unlabeled target domain, while also rejecting target classes that are not present in the source. To avoid negative transfer, OSDA can be tackled by first separating the known/unknown target samples and then aligning known target samples with the source data. We propose a novel method to addresses both these problems using the self-supervised task of rotation recognition. Moreover, we assess the performance with a new open set metric that properly balances the contribution of recognizing the known classes and rejecting the unknown samples. Comparative experiments with existing OSDA methods on the standard Office-31 and Office-Home benchmarks show that: (i) our method outperforms its competitors, (ii) reproducibility for this field is a crucial issue to tackle, (iii) our metric provides a reliable tool to allow fair open set evaluation.
Few-shot learning aims to train efficient predictive models with a few examples. The lack of training data leads to poor models that perform high-variance or low-confidence predictions. In this paper, we propose to meta-learn the ensemble of epoch-wise empirical Bayes models (E3BM) to achieve robust predictions. ""Epoch-wise"" means that each training epoch has a Bayes model whose parameters are specifically learned and deployed. ""Empirical"" means that the hyperparameters, e.g., used for learning and ensembling the epoch-wise models, are generated by hyperprior learners conditional on task-specific data. We introduce four kinds of hyperprior learners by considering inductive vs. transductive, and epoch-dependent vs. epoch-independent, in the paradigm of meta-learning. We conduct extensive experiments for five-class few-shot learning tasks on three challenging benchmarks: miniImageNet, tieredImageNet, and FC100, and achieve top performance using the epoch-dependent transductive hyperprior learner, which captures the richest information. Our ablation study shows that both ""epoch-wise ensemble"" and ""empirical"" encourage high efficiency and robustness in the model performance.
Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to address this problem through different ways to minimise the domain shift between source and target datasets. In this paper we take an orthogonal perspective and propose a framework to further enhance performance by meta-learning the initial conditions of existing DA algorithms. This is challenging compared to the more widely considered setting of few-shot meta-learning, due to the length of the computation graph involved. Therefore we propose an online shortest-path meta-learning framework that is both computationally tractable and practically effective for improving DA performance. We present variants for both multi-source unsupervised domain adaptation (MSDA), and semi-supervised domain adaptation (SSDA). Importantly, our approach is agnostic to the base adaptation algorithm, and can be applied to improve many techniques. Experimentally, we demonstrate improvements on classic (DANN) and recent (MCD and MME) techniques for MSDA and SSDA, and ultimately achieve state of the art results on several DA benchmarks including the largest scale DomainNet.
We merge by generalization two principles of passive optical sensing of motion. One is common spatially resolved imaging, where motion induces temporal readout changes at high-contrast spatial features, as used in traditional optical-flow. The other is the polarization compass, where axial rotation induces temporal readout changes due to the change of incoming polarization angle, relative to the camera frame. The latter has traditionally been modeled for uniform objects. This merger generalizes the brightness constancy assumption and optical-flow, to handle polarization. It also generalizes the polarization compass concept to handle arbitrarily textured objects. This way, scene regions having partial polarization contribute to motion estimation, irrespective of their texture and non-uniformity. As an application, we derive and demonstrate passive sensing of differential ego-rotation around the camera optical axis.
Motion plays a crucial role in understanding videos and most state-of-the-art neural models for video classification incorporate motion information typically using optical flows extracted by a separate off-the-shelf method. As the frame-by-frame optical flows require heavy computation, incorporating motion information has remained a major computational bottleneck for video understanding. In this work, we replace external and heavy computation of optical flows with internal and light-weight learning of motion features. We propose a trainable neural module, dubbed MotionSqueeze, for effective motion feature extraction. Inserted in the middle of any neural network, it learns to establish correspondences across frames and convert them into motion features, which are readily fed to the next downstream layer for better prediction. We demonstrate that the proposed method provides a significant gain on four standard benchmarks for action recognition with only a small amount of additional cost, outperforming the state of the art on Something-Something-V1&V2 datasets.
Multi-camera systems are an important sensor platform for intelligent systems such as self-driving cars. Pattern-based calibration techniques can be used to calibrate the intrinsics of the cameras individually. However, extrinsic calibration of systems with little to no visual overlap between the cameras is a challenge. Given the camera intrinsics, infrastucture-based calibration techniques are able to estimate the extrinsics using 3D maps pre-built via SLAM or Structure-from-Motion. In this paper, we propose to fully calibrate a multi-camera system from scratch using an infrastructure-based approach. Assuming that the distortion is mainly radial, we introduce a two-stage approach. We first estimate the camera-rig extrinsics up to a single unknown translation component per camera. Next, we solve for both the intrinsic parameters and the missing translation components. Extensive experiments on multiple indoor and outdoor scenes with multiple multi-camera systems show that our calibration method achieves high accuracy and robustness. In particular, our approach is more robust than the naive approach of first estimating intrinsic parameters and pose per camera before refining the extrinsic parameters of the system. The implementation is available at https://github.com/youkely/InfrasCal.
Despite the success of Lipschitz regularization in stabilizing GAN training, the exact reason of its effectiveness remains poorly understood. The direct effect of $K$-Lipschitz regularization is to restrict the $L2$-norm of the neural network gradient to be smaller than a threshold $K$ (e.g., $K=1$) such that $\| Lipschitz regularization ensures that all loss functions effectively work in the same way. Empirically, we verify our proposition on the MNIST, CIFAR10 and CelebA datasets.
Implicit surface representation combined with deep learning has led to impressive models which can represent detailed shapes of objects. Implicit surface representations, such as signed-distance functions, allow to represent shapes of arbitrary topologies. Since a continous function is learned, the reconstructions can also be extracted at any arbitrary resolution. However, large shape datasets such as Shapenet are required to train such models. In this paper, we present a mid-level patch-based surface representation. At the level of patches, objects across different categories share similarities, which leads to more generalizable models. We introduce a novel method to learn these patches in a canonical space, such that they are as object-agnostic as possible. We show that patches trained on one category of objects from ShapeNet can also represent detailed shapes from any other category as well. In addition, our patches can be trained using much fewer shapes, compared to existing approaches. We show several applications of our new representation, including shape interpolation and partial point cloud completion. Due to explicit control over patch extrinsics, our representation is also more controllable compared to object-level representations, which we demonstrate by non-rigidly deforming shapes.
Lossy image compression is pervasively conducted to save communication bandwidth, resulting in undesirable compression artifacts. Recently, extensive approaches have been proposed to reduce image compression artifacts at the decoder side; however, they require a series of architecture-identical models to process images with different quality, which are inefficient and resource-consuming. Besides, it is common in practice that compressed images are with unknown quality and it is intractable for existing approaches to select a suitable model for blind quality enhancement. In this paper, we propose a resource-efficient blind quality enhancement (RBQE) approach for compressed images. Specifically, our approach blindly and progressively enhances the quality of compressed images through a dynamic deep neural network (DNN), in which an early-exit strategy is embedded. Then, our approach can automatically decide to terminate or continue enhancement according to the assessed quality of enhanced images. Consequently, slight artifacts can be removed in a simpler and faster process, while the severe artifacts can be further removed in a more elaborate process. Extensive experiments demonstrate that our RBQE approach achieves state-of-the-art performance in terms of both blind quality enhancement and resource efficiency.
Topology change is a challenging problem for 4D reconstruction of dynamic scenes. In the classic volumetric fusion-based framework, a mesh is usually extracted from the TSDF volume as the canonical surface representation to help estimating deformation field. However, the surface and Embedded Deformation Graph (EDG) representations bring conflicts under topology changes since the surface mesh has fixed-connectivity but the deformation field can be discontinuous. In this paper, the classic framework is re-designed to enable 4D reconstruction of dynamic scene under topology changes, by introducing a novel structure of Non-manifold Volumetric Grid to the re-design of both TSDF and EDG, which allows connectivity updates by cell splitting and replication. Experiments show convincing reconstruction results for dynamic scenes of topology changes, as compared to the state-of-the-art methods.
The transferability of adversarial examples across deep neural network (DNN) models is the crux of a spectrum of black-box attacks. In this paper, we propose a novel method to enhance the black-box transferability of baseline adversarial examples. By establishing a linear mapping of the intermediate-level discrepancies (between a set of adversarial inputs and their benign counterparts) for predicting their evoked adversarial loss, we manage to take full advantage of the optimization procedure of baseline attacks. We conduct extensive experiments to verify the effectiveness of our method on CIFAR-100 and ImageNet. Experimental results demonstrate that it outperforms previous state-of-the-arts by large margins. Our code will be made publicly available.
A key capability of an intelligent system is deciding when events from past experience must be remembered and when they can be forgotten. Towards this goal, we develop a predictive model of human visual event memory and how those memories decay over time. We introduce Memento10k, a new, dynamic video memorability dataset containing human annotations at different viewing delays. Based on our findings, we propose a new mathematical formulation of memorability decay, resulting in a model that is able to produce the first quantitative estimation of how a video decays in memory over time. In contrast with previous work, our model can predict the probability that a video will be remembered at an arbitrary delay. Importantly, our approach combines visual and semantic information (in the form of textual captions) to fully represent the meaning of events. Our experiments on two video memorability benchmarks, including Memento10k, show that our model significantly improves upon the best prior approach (by 12% on average).
We introduce the first dense neural non-rigid structure from motion (N-NRSfM) approach, which can be trained end-to-end in an unsupervised manner from 2D point tracks. Compared to the competing methods, our combination of loss functions is fully-differentiable and can be readily integrated into deep-learning systems. We formulate the deformation model by an auto-decoder and impose subspace constraints on the recovered latent space function in a frequency domain. Thanks to the state recurrence cue, we classify the reconstructed non-rigid surfaces based on their similarity and recover the period of the input sequence. Our N-NRSfM approach achieves competitive accuracy on widely-used benchmark sequences and high visual quality on various real videos. Apart from being a standalone technique, our method enables multiple applications including shape compression, completion and interpolation, among others. Combined with an encoder trained directly on 2D images, we perform scenario-specific monocular 3D shape reconstruction at interactive frame rates. To facilitate the reproducibility of the results and boost the new research direction, we open-source our code and provide trained models for research purposes.
We present a novel method to reconstruct the 3D layout of a room—walls, floors, ceilings—from a single perspective view in challenging conditions, by contrast with previous single-view methods restricted to cuboid-shaped layouts. This input view can consist of a color image only, but considering a depth map results in a more accurate reconstruction. Our approach is formalized as solving a constrained discrete optimization problem to find the set of 3D polygons that constitute the layout. In order to deal with occlusions between components of the layout, which is a problem ignored by previous works, we introduce an analysis-by-synthesis method to iteratively refine the 3D layout estimate. As no dataset was available to evaluate our method quantitatively, we created one together with several appropriate metrics. Our dataset consists of 293 images from ScanNet, which we annotated with precise 3D layouts. It offers three times more samples than the popular NYUv2 303 benchmark, and a much larger variety of layouts.
Stochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition
PDF ↗In this paper, we propose novel stochastic modeling of various components of a continuous sign language recognition (CSLR) system that is based on the transformer encoder and connectionist temporal classification (CTC). Most importantly, We model each sign gloss with multiple states, and the number of states is a categorical random variable that follows a learned probability distribution, providing stochastic fine-grained labels for training the CTC decoder. We further propose a stochastic frame dropping mechanism and a gradient stopping method to deal with the severe overfitting problem in training the transformer model with CTC loss. These two methods also help reduce the training computation, both in terms of time and space, significantly. We evaluated our model on popular CSLR datasets, and show its effectiveness compared to the state-of-the-art methods.