Paper Group NAWR 8
IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition. Gendered Ambiguous Pronouns Shared Task: Boosting Model Confidence by Evidence Pooling. Neural Relational Inference with Fast Modular Meta-learning. Multiple Futures Prediction. Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Human …
IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition
| Title | IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition |
| Authors | Xiaoping Wu, Chi Zhan, Yu-Kun Lai, Ming-Ming Cheng, Jufeng Yang |
| Abstract | Insect pests are one of the main factors affecting agricultural product yield. Accurate recognition of insect pests facilitates timely preventive measures to avoid economic losses. However, the existing datasets for the visual classification task mainly focus on common objects, e.g., flowers and dogs. This limits the application of powerful deep learning technology on specific domains like the agricultural field. In this paper, we collect a large-scale dataset named IP102 for insect pest recognition. Specifically, it contains more than 75, 000 images belonging to 102 categories, which exhibit a natural long-tailed distribution. In addition, we annotate about 19, 000 images with bounding boxes for object detection. The IP102 has a hierarchical taxonomy and the insect pests which mainly affect one specific agricultural product are grouped into the same upperlevel category. Furthermore, we perform several baseline experiments on the IP102 dataset, including handcrafted and deep feature based classification methods. Experimental results show that this dataset has the challenges of interand intra- class variance and data imbalance. We believe our IP102 will facilitate future research on practical insect pest control, fine-grained visual classification, and imbalanced learning fields. We make the dataset and pre-trained models publicly available at https://github.com/xpwu95/IP102. |
| Tasks | Fine-Grained Image Classification, Object Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wu_IP102_A_Large-Scale_Benchmark_Dataset_for_Insect_Pest_Recognition_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wu_IP102_A_Large-Scale_Benchmark_Dataset_for_Insect_Pest_Recognition_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/ip102-a-large-scale-benchmark-dataset-for |
| Repo | https://github.com/xpwu95/IP102 |
| Framework | none |
Gendered Ambiguous Pronouns Shared Task: Boosting Model Confidence by Evidence Pooling
| Title | Gendered Ambiguous Pronouns Shared Task: Boosting Model Confidence by Evidence Pooling |
| Authors | S Attree, eep |
| Abstract | This paper presents a strong set of results for resolving gendered ambiguous pronouns on the Gendered Ambiguous Pronouns shared task. The model presented here draws upon the strengths of state-of-the-art language and coreference resolution models, and introduces a novel evidence-based deep learning architecture. Injecting evidence from the coreference models compliments the base architecture, and analysis shows that the model is not hindered by their weaknesses, specifically gender bias. The modularity and simplicity of the architecture make it very easy to extend for further improvement and applicable to other NLP problems. Evaluation on GAP test data results in a state-of-the-art performance at 92.5{%} F1 (gender bias of 0.97), edging closer to the human performance of 96.6{%}. The end-to-end solution presented here placed 1st in the Kaggle competition, winning by a significant lead. |
| Tasks | Coreference Resolution |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3820/ |
| https://www.aclweb.org/anthology/W19-3820 | |
| PWC | https://paperswithcode.com/paper/gendered-ambiguous-pronouns-shared-task |
| Repo | https://github.com/sattree/gap |
| Framework | tf |
Neural Relational Inference with Fast Modular Meta-learning
| Title | Neural Relational Inference with Fast Modular Meta-learning |
| Authors | Ferran Alet, Erica Weng, Tomás Lozano-Pérez, Leslie Pack Kaelbling |
| Abstract | Graph neural networks (GNNs) are effective models for many dynamical systems consisting of entities and relations. Although most GNN applications assume a single type of entity and relation, many situations involve multiple types of interactions. Relational inference is the problem of inferring these interactions and learning the dynamics from observational data. We frame relational inference as a modular meta-learning problem, where neural modules are trained to be composed in different ways to solve many tasks. This meta-learning framework allows us to implicitly encode time invariance and infer relations in context of one another rather than independently, which increases inference capacity. Framing inference as the inner-loop optimization of meta-learning leads to a model-based approach that is more data-efficient and capable of estimating the state of entities that we do not observe directly, but whose existence can be inferred from their effect on observed entities. To address the large search space of graph neural network compositions, we meta-learn a proposal function that speeds up the inner-loop simulated annealing search within the modular meta-learning algorithm, providing two orders of magnitude increase in the size of problems that can be addressed. |
| Tasks | Meta-Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9353-neural-relational-inference-with-fast-modular-meta-learning |
| http://papers.nips.cc/paper/9353-neural-relational-inference-with-fast-modular-meta-learning.pdf | |
| PWC | https://paperswithcode.com/paper/neural-relational-inference-with-fast-modular |
| Repo | https://github.com/FerranAlet/modular-metalearning |
| Framework | pytorch |
Multiple Futures Prediction
| Title | Multiple Futures Prediction |
| Authors | Charlie Tang, Russ R. Salakhutdinov |
| Abstract | Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcomes, due to multi-agent interactions and the latent goals of others. Towards these goals, we introduce a probabilistic framework that efficiently learns latent variables to jointly model the multi-step future motions of agents in a scene. Our framework is data-driven and learns semantically meaningful latent variables to represent the multimodal future, without requiring explicit labels. Using a dynamic attention-based state encoder, we learn to encode the past as well as the future interactions among agents, efficiently scaling to any number of agents. Finally, our model can be used for planning via computing a conditional probability density over the trajectories of other agents given a hypothetical rollout of the ego agent. We demonstrate our algorithms by predicting vehicle trajectories of both simulated and real data, demonstrating the state-of-the-art results on several vehicle trajectory datasets. |
| Tasks | motion prediction |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9676-multiple-futures-prediction |
| http://papers.nips.cc/paper/9676-multiple-futures-prediction.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-futures-prediction-1 |
| Repo | https://github.com/apple/ml-multiple-futures-prediction |
| Framework | none |
Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Humanities
| Title | Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Humanities |
| Authors | Alex Erdmann, er, David Joseph Wrisley, Benjamin Allen, Christopher Brown, Sophie Cohen-Bod{'e}n{`e}s, Micha Elsner, Yukun Feng, Brian Joseph, B{'e}atrice Joyeux-Prunel, Marie-Catherine de Marneffe |
| Abstract | Scholars in inter-disciplinary fields like the Digital Humanities are increasingly interested in semantic annotation of specialized corpora. Yet, under-resourced languages, imperfect or noisily structured data, and user-specific classification tasks make it difficult to meet their needs using off-the-shelf models. Manual annotation of large corpora from scratch, meanwhile, can be prohibitively expensive. Thus, we propose an active learning solution for named entity recognition, attempting to maximize a custom model{'}s improvement per additional unit of manual annotation. Our system robustly handles any domain or user-defined label set and requires no external resources, enabling quality named entity recognition for Humanities corpora where such resources are not available. Evaluating on typologically disparate languages and datasets, we reduce required annotation by 20-60{%} and greatly outperform a competitive active learning baseline. |
| Tasks | Active Learning, Named Entity Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1231/ |
| https://www.aclweb.org/anthology/N19-1231 | |
| PWC | https://paperswithcode.com/paper/practical-efficient-and-customizable-active |
| Repo | https://github.com/alexerdmann/Herodotos-Project-Latin-NER-Tagger-Annotation |
| Framework | none |
Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning
| Title | Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning |
| Authors | Erwan Lecarpentier, Emmanuel Rachelson |
| Abstract | This work tackles the problem of robust zero-shot planning in non-stationary stochastic environments. We study Markov Decision Processes (MDPs) evolving over time and consider Model-Based Reinforcement Learning algorithms in this setting. We make two hypotheses: 1) the environment evolves continuously with a bounded evolution rate; 2) a current model is known at each decision epoch but not its evolution. Our contribution can be presented in four points. 1) we define a specific class of MDPs that we call Non-Stationary MDPs (NSMDPs). We introduce the notion of regular evolution by making an hypothesis of Lipschitz-Continuity on the transition and reward functions w.r.t. time; 2) we consider a planning agent using the current model of the environment but unaware of its future evolution. This leads us to consider a worst-case method where the environment is seen as an adversarial agent; 3) following this approach, we propose the Risk-Averse Tree-Search (RATS) algorithm, a zero-shot Model-Based method similar to Minimax search; 4) we illustrate the benefits brought by RATS empirically and compare its performance with reference Model-Based algorithms. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8942-non-stationary-markov-decision-processes-a-worst-case-approach-using-model-based-reinforcement-learning |
| http://papers.nips.cc/paper/8942-non-stationary-markov-decision-processes-a-worst-case-approach-using-model-based-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/non-stationary-markov-decision-processes-a-1 |
| Repo | https://github.com/SuReLI/rats-experiments |
| Framework | none |
Correlation-Sensitive Next-Basket Recommendation
| Title | Correlation-Sensitive Next-Basket Recommendation |
| Authors | Duc-Trong Le, Hady W. Lauw, Yuan Fang |
| Abstract | Items adopted by a user over time are indicative of the underlying preferences. We are concerned with learning such preferences from observed sequences of adoptions for recommendation. As multiple items are commonly adopted concurrently, e.g., a basket of grocery items or a sitting of media consumption, we deal with a sequence of baskets as input, and seek to recommend the next basket. Intuitively, a basket tends to contain groups of related items that support particular needs. Instead of recommending items independently for the next basket, we hypothesize that incorporating information on pairwise correlations among items would help to arrive at more coherent basket recommendations. Towards this objective, we develop a hierarchical network architecture codenamed Beacon to model basket sequences. Each basket is encoded taking into account the relative importance of items and correlations among item pairs. This encoding is utilized to infer sequential associations along the basket sequence. Extensive experiments on three public real-life datasets showcase the effectiveness of our approach for the next-basket recommendation problem. |
| Tasks | |
| Published | 2019-08-10 |
| URL | https://www.ijcai.org/Proceedings/2019/389 |
| https://www.ijcai.org/proceedings/2019/0389.pdf | |
| PWC | https://paperswithcode.com/paper/correlation-sensitive-next-basket |
| Repo | https://github.com/PreferredAI/beacon |
| Framework | tf |
muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking
| Title | muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking |
| Authors | Congchao Wang, Yizhi Wang, Yinxue Wang, Chiung-Ting Wu, Guoqiang Yu |
| Abstract | Min-cost flow has been a widely used paradigm for solving data association problems in multi-object tracking (MOT). However, most existing methods of solving min-cost flow problems in MOT are either direct adoption or slight modifications of generic min-cost flow algorithms, yielding sub-optimal computation efficiency and holding the applications back from larger scale of problems. In this paper, by exploiting the special structures and properties of the graphs formulated in MOT problems, we develop an efficient min-cost flow algorithm, namely, minimum-update Successive Shortest Path (muSSP). muSSP is proved to provide exact optimal solution and we demonstrated its efficiency through 40 experiments on five MOT datasets with various object detection results and a number of graph designs. muSSP is always the most efficient in each experiment compared to the three peer solvers, improving the efficiency by 5 to 337 folds relative to the best competing algorithm and averagely 109 to 4089 folds to each of the three peer methods. |
| Tasks | Multi-Object Tracking, Object Detection, Object Tracking |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8334-mussp-efficient-min-cost-flow-algorithm-for-multi-object-tracking |
| http://papers.nips.cc/paper/8334-mussp-efficient-min-cost-flow-algorithm-for-multi-object-tracking.pdf | |
| PWC | https://paperswithcode.com/paper/mussp-efficient-min-cost-flow-algorithm-for |
| Repo | https://github.com/yu-lab-vt/muSSP |
| Framework | none |
Primal-Dual Block Generalized Frank-Wolfe
| Title | Primal-Dual Block Generalized Frank-Wolfe |
| Authors | Qi Lei, Jiacheng Zhuo, Constantine Caramanis, Inderjit S. Dhillon, Alexandros G. Dimakis |
| Abstract | We propose a generalized variant of Frank-Wolfe algorithm for solving a class of sparse/low-rank optimization problems. Our formulation includes Elastic Net, regularized SVMs and phase retrieval as special cases. The proposed Primal-Dual Block Generalized Frank-Wolfe algorithm reduces the per-iteration cost while maintaining linear convergence rate. The per iteration cost of our method depends on the structural complexity of the solution (i.e. sparsity/low-rank) instead of the ambient dimension. We empirically show that our algorithm outperforms the state-of-the-art methods on (multi-class) classification tasks. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9538-primal-dual-block-generalized-frank-wolfe |
| http://papers.nips.cc/paper/9538-primal-dual-block-generalized-frank-wolfe.pdf | |
| PWC | https://paperswithcode.com/paper/primal-dual-block-generalized-frank-wolfe |
| Repo | https://github.com/CarlsonZhuo/primal_dual_frank_wolfe |
| Framework | none |
Image Recoloring Based on Object Color Distributions
| Title | Image Recoloring Based on Object Color Distributions |
| Authors | Mahmoud Afifi, Brian Price, Scott Cohen, and Michael S. Brown |
| Abstract | We present a method to perform automatic image recoloring based on the distribution of colors associated with objects present in an image. For example, when recoloring an image containing a sky object, our method incorporates the observation that objects of class ‘sky’ have a color distribution with three dominant modes for blue (daytime), yellow/red (dusk/dawn), and dark (nighttime). Our work leverages recent deep-learning methods that can perform reasonably accurate object-level segmentation. By using the images in datasets used to train deep-learning object segmentation methods, we are able to model the color distribution of each object class in the dataset. Given a new input image and its associated semantic segmentation (i.e., object mask), we perform color transfer to map the input image color histogram to a set of target color histograms that were constructed based on the learned color distribution of the objects in the image. We show that our framework is able to produce compelling color variations that are often more interesting and unique than results produced by existing methods. |
| Tasks | Semantic Segmentation |
| Published | 2019-05-06 |
| URL | https://diglib.eg.org/handle/10.2312/egs20191008 |
| http://cvil.eecs.yorku.ca/projects/public_html/image_recoloring/files/Image_Recoloring_Based_on_Object_Color_Distributions.pdf | |
| PWC | https://paperswithcode.com/paper/image-recoloring-based-on-object-color |
| Repo | https://github.com/mahmoudnafifi/Image_recoloring |
| Framework | none |
Optimal Sampling and Clustering in the Stochastic Block Model
| Title | Optimal Sampling and Clustering in the Stochastic Block Model |
| Authors | Se-Young Yun, Alexandre Proutiere |
| Abstract | This paper investigates the design of joint adaptive sampling and clustering algorithms in networks whose structure follows the celebrated Stochastic Block Model (SBM). To extract hidden clusters, the interaction between edges (pairs of nodes) may be sampled sequentially, in an adaptive manner. After gathering samples, the learner returns cluster estimates. We derive information-theoretical upper bounds on the cluster recovery rate. These bounds actually reveal the optimal sequential edge sampling strategy, and interestingly, the latter does not depend on the sampling budget, but on the parameters of the SBM only. We devise a joint sampling and clustering algorithm matching the recovery rate upper bounds. The algorithm initially uses a fraction of the sampling budget to estimate the SBM parameters, and to learn the optimal sampling strategy. This strategy then guides the remaining sampling process, which confers the optimality of the algorithm. We show both analytically and numerically that adaptive edge sampling yields important improvements over random sampling (traditionally used in the SBM analysis). For example, we prove that adaptive sampling significantly enlarges the region of the SBM parameters where asymptotically exact cluster recovery is feasible. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9498-optimal-sampling-and-clustering-in-the-stochastic-block-model |
| http://papers.nips.cc/paper/9498-optimal-sampling-and-clustering-in-the-stochastic-block-model.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-sampling-and-clustering-in-the |
| Repo | https://github.com/fbsqkd/StochasticBlockModel |
| Framework | none |
MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization
| Title | MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization |
| Authors | Shangyu Chen, Wenya Wang, Sinno Jialin Pan |
| Abstract | Tremendous amount of parameters make deep neural networks impractical to be deployed for edge-device-based real-world applications due to the limit of computational power and storage space. Existing studies have made progress on learning quantized deep models to reduce model size and energy consumption, i.e. converting full-precision weights ($r$'s) into discrete values ($q$'s) in a supervised training manner. However, the training process for quantization is non-differentiable, which leads to either infinite or zero gradients ($g_r$) w.r.t. $r$. To address this problem, most training-based quantization methods use the gradient w.r.t. $q$ ($g_q$) with clipping to approximate $g_r$ by Straight-Through-Estimator (STE) or manually design their computation. However, these methods only heuristically make training-based quantization applicable, without further analysis on how the approximated gradients can assist training of a quantized network. In this paper, we propose to learn $g_r$ by a neural network. Specifically, a meta network is trained using $g_q$ and $r$ as inputs, and outputs $g_r$ for subsequent weight updates. The meta network is updated together with the original quantized network. Our proposed method alleviates the problem of non-differentiability, and can be trained in an end-to-end manner. Extensive experiments are conducted with CIFAR10/100 and ImageNet on various deep networks to demonstrate the advantage of our proposed method in terms of a faster convergence rate and better performance. Codes are released at: \texttt{https://github.com/csyhhu/MetaQuant} |
| Tasks | Quantization |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8647-metaquant-learning-to-quantize-by-learning-to-penetrate-non-differentiable-quantization |
| http://papers.nips.cc/paper/8647-metaquant-learning-to-quantize-by-learning-to-penetrate-non-differentiable-quantization.pdf | |
| PWC | https://paperswithcode.com/paper/metaquant-learning-to-quantize-by-learning-to |
| Repo | https://github.com/csyhhu/MetaQuant |
| Framework | pytorch |
Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning
| Title | Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning |
| Authors | Xinyang Chen, Sinan Wang, Bo Fu, Mingsheng Long, Jianmin Wang |
| Abstract | Before sufficient training data is available, fine-tuning neural networks pre-trained on large-scale datasets substantially outperforms training from random initialization. However, fine-tuning methods suffer from two dilemmas, catastrophic forgetting and negative transfer. While several methods with explicit attempts to overcome catastrophic forgetting have been proposed, negative transfer is rarely delved into. In this paper, we launch an in-depth empirical investigation into negative transfer in fine-tuning and find that, for the weight parameters and feature representations, transferability of their spectral components is diverse. For safe transfer learning, we present Batch Spectral Shrinkage (BSS), a novel regularization approach to penalizing smaller singular values so that untransferable spectral components are suppressed. BSS is orthogonal to existing fine-tuning methods and is readily pluggable to them. Experimental results show that BSS can significantly enhance the performance of representative methods, especially with limited training data. |
| Tasks | Transfer Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8466-catastrophic-forgetting-meets-negative-transfer-batch-spectral-shrinkage-for-safe-transfer-learning |
| http://papers.nips.cc/paper/8466-catastrophic-forgetting-meets-negative-transfer-batch-spectral-shrinkage-for-safe-transfer-learning.pdf | |
| PWC | https://paperswithcode.com/paper/catastrophic-forgetting-meets-negative |
| Repo | https://github.com/thuml/Batch-Spectral-Shrinkage |
| Framework | pytorch |
Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting
| Title | Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting |
| Authors | Shengnan Guo, 1, 2 Youfang Lin, 1, 2, 3 Ning Feng, 1, 3 Chao Song, 1, 2 Huaiyu Wan 1, 2, 3∗ |
| Abstract | Forecasting the traffic flows is a critical issue for researchers and practitioners in the field of transportation. However, it is very challenging since the traffic flows usually show high nonlinearities and complex patterns. Most existing traffic flow prediction methods, lacking abilities of modeling the dynamic spatial-temporal correlations of traffic data, thus cannot yield satisfactory prediction results. In this paper, we propose a novel attention based spatial-temporal graph convolutional network (ASTGCN) model to solve traffic flow forecasting problem. ASTGCN mainly consists of three independent components to respectively model three temporal properties of traffic flows, i.e., recent, daily-periodic and weekly-periodic dependencies. More specifically, each component contains two major parts: 1) the spatial-temporal attention mechanism to effectively capture the dynamic spatialtemporal correlations in traffic data; 2) the spatial-temporal convolution which simultaneously employs graph convolutions to capture the spatial patterns and common standard convolutions to describe the temporal features. The output of the three components are weighted fused to generate the final prediction results. Experiments on two real-world datasets from the Caltrans Performance Measurement System (PeMS) demonstrate that the proposed ASTGCN model outperforms the state-of-the-art baselines. |
| Tasks | |
| Published | 2019-01-20 |
| URL | https://aaai.org/ojs/index.php/AAAI/article/view/3881 |
| https://aaai.org/ojs/index.php/AAAI/article/view/3881 | |
| PWC | https://paperswithcode.com/paper/attention-based-spatial-temporal-graph |
| Repo | https://github.com/Davidham3/ASTGCN |
| Framework | mxnet |
Approximated Bilinear Modules for Temporal Modeling
| Title | Approximated Bilinear Modules for Temporal Modeling |
| Authors | Xinqi Zhu, Chang Xu, Langwen Hui, Cewu Lu, Dacheng Tao |
| Abstract | We consider two less-emphasized temporal properties of video: 1. Temporal cues are fine-grained; 2. Temporal modeling needs reasoning. To tackle both problems at once, we exploit approximated bilinear modules (ABMs) for temporal modeling. There are two main points making the modules effective: two-layer MLPs can be seen as a constraint approximation of bilinear operations, thus can be used to construct deep ABMs in existing CNNs while reusing pretrained parameters; frame features can be divided into static and dynamic parts because of visual repetition in adjacent frames, which enables temporal modeling to be more efficient. Multiple ABM variants and implementations are investigated, from high performance to high efficiency. Specifically, we show how two-layer subnets in CNNs can be converted to temporal bilinear modules by adding an auxiliary-branch. Besides, we introduce snippet sampling and shifting inference to boost sparse-frame video classification performance. Extensive ablation studies are conducted to show the effectiveness of proposed techniques. Our models can outperform most state-of-the-art methods on Something-Something v1 and v2 datasets without Kinetics pretraining, and are also competitive on other YouTube-like action recognition datasets. Our code is available on https://github.com/zhuxinqimac/abm-pytorch. |
| Tasks | Video Classification |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhu_Approximated_Bilinear_Modules_for_Temporal_Modeling_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhu_Approximated_Bilinear_Modules_for_Temporal_Modeling_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/approximated-bilinear-modules-for-temporal |
| Repo | https://github.com/zhuxinqimac/abm-pytorch |
| Framework | pytorch |
