arXiv subjects

Songyang Zhang

Publications and source records attributed to Songyang Zhang.

At least 127 records · Page 7Linked to original sources

arXiv2022

Action Quality Assessment with Temporal Parsing Transformer

Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences. Existing state-of-the-art methods typically rely on the holistic video representations for score regression or ranking, which limits the generalization to capture fine-grained intra-class variation. To overcome the above limitation, we propose a temporal parsing transformer to decompose the holistic feature into temporal part-level representations. Specifically, we utilize a set of learnable queries to represent the atomic temporal patterns for a specific action. Our decoding process converts the frame representations to a fixed number of temporally ordered part representations. To obtain the quality score, we adopt the state-of-the-art contrastive regression based on the part representations. Since existing AQA datasets do not provide temporal part-level labels or partitions, we propose two novel loss functions on the cross attention responses of the decoder: a ranking loss to ensure the learnable queries to satisfy the temporal order in cross attention and a sparsity loss to encourage the part representations to be more discriminative. Extensive experiments show that our proposed method outperforms prior work on three public AQA benchmarks by a considerable margin.

cs.CV↗

arXiv2022

The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

Unbiased SGG has achieved significant progress over recent years. However, almost all existing SGG models have overlooked the ground-truth annotation qualities of prevailing SGG datasets, i.e., they always assume: 1) all the manually annotated positive samples are equally correct; 2) all the un-annotated negative samples are absolutely background. In this paper, we argue that both assumptions are inapplicable to SGG: there are numerous "noisy" groundtruth predicate labels that break these two assumptions, and these noisy samples actually harm the training of unbiased SGG models. To this end, we propose a novel model-agnostic NoIsy label CorrEction strategy for SGG: NICE. NICE can not only detect noisy samples but also reassign more high-quality predicate labels to them. After the NICE training, we can obtain a cleaner version of SGG dataset for model training. Specifically, NICE consists of three components: negative Noisy Sample Detection (Neg-NSD), positive NSD (Pos-NSD), and Noisy Sample Correction (NSC). Firstly, in Neg-NSD, we formulate this task as an out-of-distribution detection problem, and assign pseudo labels to all detected noisy negative samples. Then, in Pos-NSD, we use a clustering-based algorithm to divide all positive samples into multiple sets, and treat the samples in the noisiest set as noisy positive samples. Lastly, in NSC, we use a simple but effective weighted KNN to reassign new predicate labels to noisy positive samples. Extensive results on different backbones and tasks have attested to the effectiveness and generalization abilities of each component of NICE.

cs.CV↗

arXiv2022

MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration

Multimodal video-audio-text understanding and generation can benefit from datasets that are narrow but rich. The narrowness allows bite-sized challenges that the research community can make progress on. The richness ensures we are making progress along the core challenges. To this end, we present a large-scale video-audio-text dataset MUGEN, collected using the open-sourced platform game CoinRun [11]. We made substantial modifications to make the game richer by introducing audio and enabling new interactions. We trained RL agents with different objectives to navigate the game and interact with 13 objects and characters. This allows us to automatically extract a large collection of diverse videos and associated audio. We sample 375K video clips (3.2s each) and collect text descriptions from human annotators. Each video has additional annotations that are extracted automatically from the game engine, such as accurate semantic maps for each frame and templated textual descriptions. Altogether, MUGEN can help progress research in many tasks in multimodal understanding and generation. We benchmark representative approaches on tasks involving video-audio-text retrieval and generation. Our dataset and code are released at: https://mugen-org.github.io/.

cs.CV↗

arXiv2022

Image Processing via Multilayer Graph Spectra

Graph signal processing (GSP) has become an important tool in image processing because of its ability to reveal underlying data structures. Many real-life multimedia datasets, however, exhibit heterogeneous structures across frames. Multilayer graphs (MLG), instead of traditional single-layer graphs, provide better representation of these datasets such as videos and hyperspectral images. To generalize GSP to multilayer graph models and develop multilayer analysis for image processing, this work introduces a tensor-based framework of multilayer graph signal processing (M-GSP) and present useful M-GSP tools for image processing. We then present guidelines for applying M-GSP in image processing and introduce several applications, including RGB image compression, edge detection and hyperspectral image segmentation. Successful experimental results demonstrate the efficacy and promising futures of M-GSP in image processing.

eess.SP↗

arXiv2022

SGTR: End-to-end Scene Graph Generation with Transformer

Scene Graph Generation (SGG) remains a challenging visual understanding task due to its compositional property. Most previous works adopt a bottom-up two-stage or a point-based one-stage approach, which often suffers from high time complexity or sub-optimal designs. In this work, we propose a novel SGG method to address the aforementioned issues, formulating the task as a bipartite graph construction problem. To solve the problem, we develop a transformer-based end-to-end framework that first generates the entity and predicate proposal set, followed by inferring directed edges to form the relation triplets. In particular, we develop a new entity-aware predicate representation based on a structural predicate generator that leverages the compositional property of relationships. Moreover, we design a graph assembling module to infer the connectivity of the bipartite scene graph based on our entity-aware structure, enabling us to generate the scene graph in an end-to-end manner. Extensive experimental results show that our design is able to achieve the state-of-the-art or comparable performance on two challenging benchmarks, surpassing most of the existing approaches and enjoying higher efficiency in inference. We hope our model can serve as a strong baseline for the Transformer-based scene graph generation. Code is available: https://github.com/Scarecrow0/SGTR

cs.CV↗

arXiv2022

Budget-aware Few-shot Learning via Graph Convolutional Network

This paper tackles the problem of few-shot learning, which aims to learn new visual concepts from a few examples. A common problem setting in few-shot classification assumes random sampling strategy in acquiring data labels, which is inefficient in practical applications. In this work, we introduce a new budget-aware few-shot learning problem that not only aims to learn novel object categories, but also needs to select informative examples to annotate in order to achieve data efficiency. We develop a meta-learning strategy for our budget-aware few-shot learning task, which jointly learns a novel data selection policy based on a Graph Convolutional Network (GCN) and an example-based few-shot classifier. Our selection policy computes a context-sensitive representation for each unlabeled data by graph message passing, which is then used to predict an informativeness score for sequential selection. We validate our method by extensive experiments on the mini-ImageNet, tiered-ImageNet and Omniglot datasets. The results show our few-shot learning strategy outperforms baselines by a sizable margin, which demonstrates the efficacy of our method.

cs.CV↗

arXiv2021

Hyperspectral Image Segmentation based on Graph Processing over Multilayer Networks

Hyperspectral imaging is an important sensing technology with broad applications and impact in areas including environmental science, weather, and geo/space exploration. One important task of hyperspectral image (HSI) processing is the extraction of spectral-spatial features. Leveraging on the recent-developed graph signal processing over multilayer networks (M-GSP), this work proposes several approaches to HSI segmentation based on M-GSP feature extraction. To capture joint spectral-spatial information, we first customize a tensor-based multilayer network (MLN) model for HSI, and define a MLN singular space for feature extraction. We then develop an unsupervised HSI segmentation method by utilizing MLN spectral clustering. Regrouping HSI pixels via MLN-based clustering, we further propose a semi-supervised HSI classification based on multi-resolution fusions of superpixels. Our experimental results demonstrate the strength of M-GSP in HSI processing and spectral-spatial information extraction.

cs.CV↗

arXiv2021

Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language

We address the problem of retrieving a specific moment from an untrimmed video by natural language. It is a challenging problem because a target moment may take place in the context of other temporal moments in the untrimmed video. Existing methods cannot tackle this challenge well since they do not fully consider the temporal contexts between temporal moments. In this paper, we model the temporal context between video moments by a set of predefined two-dimensional maps under different temporal scales. For each map, one dimension indicates the starting time of a moment and the other indicates the duration. These 2D temporal maps can cover diverse video moments with different lengths, while representing their adjacent contexts at different temporal scales. Based on the 2D temporal maps, we propose a Multi-Scale Temporal Adjacent Network (MS-2D-TAN), a single-shot framework for moment localization. It is capable of encoding the adjacent temporal contexts at each scale, while learning discriminative features for matching video moments with referring expressions. We evaluate the proposed MS-2D-TAN on three challenging benchmarks, i.e., Charades-STA, ActivityNet Captions, and TACoS, where our MS-2D-TAN outperforms the state of the art.

cs.CV↗

arXiv2021

Point Cloud Resampling Through Hypergraph Signal Processing

Three-dimensional (3D) point clouds are important data representations in visualization applications. The rapidly growing utility and popularity of point cloud processing strongly motivate a plethora of research activities on large-scale point cloud processing and feature extraction. In this work, we investigate point cloud resampling based on hypergraph signal processing (HGSP). We develop a novel method to extract sharp object features and reduce the data size of point cloud representation. By directly estimating hypergraph spectrum based on hypergraph stationary processing, we design a spectral kernel-based filter to capture high-dimensional interactions among point signal nodes and to better preserve object surface outlines. Experimental results validate the effectiveness of hypergraph in representing point clouds, and demonstrate the robustness of the proposed algorithm under noise.

eess.SP↗

arXiv2021

SAT: 2D Semantics Assisted Training for 3D Visual Grounding

3D visual grounding aims at grounding a natural language description about a 3D scene, usually represented in the form of 3D point clouds, to the targeted object region. Point clouds are sparse, noisy, and contain limited semantic information compared with 2D images. These inherent limitations make the 3D visual grounding problem more challenging. In this study, we propose 2D Semantics Assisted Training (SAT) that utilizes 2D image semantics in the training stage to ease point-cloud-language joint representation learning and assist 3D visual grounding. The main idea is to learn auxiliary alignments between rich, clean 2D object representations and the corresponding objects or mentioned entities in 3D scenes. SAT takes 2D object semantics, i.e., object label, image feature, and 2D geometric feature, as the extra input in training but does not require such inputs during inference. By effectively utilizing 2D semantics in training, our approach boosts the accuracy on the Nr3D dataset from 37.7% to 49.2%, which significantly surpasses the non-SAT baseline with the identical network architecture and inference input. Our approach outperforms the state of the art by large margins on multiple 3D visual grounding datasets, i.e., +10.4% absolute accuracy on Nr3D, +9.9% on Sr3D, and +5.6% on ScanRef.

cs.CV↗

arXiv2021

An EM Framework for Online Incremental Learning of Semantic Segmentation

Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acquire novel classes in an online fashion for the segmentation task, mainly due to its continuously-evolving semantic label space, partial pixelwise ground-truth annotations, and constrained data availability. To ad- dress this, we propose an incremental learning strategy that can fast adapt deep segmentation models without catastrophic forgetting, using a streaming input data with pixel annotations on the novel classes only. To this end, we develop a uni ed learning strategy based on the Expectation-Maximization (EM) framework, which integrates an iterative relabeling strategy that lls in the missing labels and a rehearsal-based incremental learning step that balances the stability-plasticity of the model. Moreover, our EM algorithm adopts an adaptive sampling method to select informative train- ing data and a class-balancing training strategy in the incremental model updates, both improving the e cacy of model learning. We validate our approach on the PASCAL VOC 2012 and ADE20K datasets, and the results demonstrate its superior performance over the existing incremental methods.

cs.CV↗

arXiv2021

Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge

In this report, we introduce our real-time 2D object detection system for the realistic autonomous driving scenario. Our detector is built on a newly designed YOLO model, called YOLOX. On the Argoverse-HD dataset, our system achieves 41.0 streaming AP, which surpassed second place by 7.8/6.1 on detection-only track/fully track, respectively. Moreover, equipped with TensorRT, our model achieves the 30FPS inference speed with a high-resolution input size (e.g., 1440-2304). Code and models will be available at https://github.com/Megvii-BaseDetection/YOLOX

cs.CV↗

arXiv2021

Learning Implicit Temporal Alignment for Few-shot Video Classification

Few-shot video classification aims to learn new video categories with only a few labeled examples, alleviating the burden of costly annotation in real-world applications. However, it is particularly challenging to learn a class-invariant spatial-temporal representation in such a setting. To address this, we propose a novel matching-based few-shot learning strategy for video sequences in this work. Our main idea is to introduce an implicit temporal alignment for a video pair, capable of estimating the similarity between them in an accurate and robust manner. Moreover, we design an effective context encoding module to incorporate spatial and feature channel context, resulting in better modeling of intra-class variations. To train our model, we develop a multi-task loss for learning video matching, leading to video features with better generalization. Extensive experimental results on two challenging benchmarks, show that our method outperforms the prior arts with a sizable margin on SomethingSomething-V2 and competitive results on Kinetics.

cs.CV↗

arXiv2021

Video-aided Unsupervised Grammar Induction

We investigate video-aided grammar induction, which learns a constituency parser from both unlabeled text and its corresponding video. Existing methods of multi-modal grammar induction focus on learning syntactic grammars from text-image pairs, with promising results showing that the information from static images is useful in induction. However, videos provide even richer information, including not only static objects but also actions and state changes useful for inducing verb phrases. In this paper, we explore rich features (e.g. action, object, scene, audio, face, OCR and speech) from videos, taking the recent Compound PCFG model as the baseline. We further propose a Multi-Modal Compound PCFG model (MMC-PCFG) to effectively aggregate these rich features from different modalities. Our proposed MMC-PCFG is trained end-to-end and outperforms each individual modality and previous state-of-the-art systems on three benchmarks, i.e. DiDeMo, YouCook2 and MSRVTT, confirming the effectiveness of leveraging video information for unsupervised grammar induction.

cs.CV↗

arXiv2021

Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation

Scene graph generation is an important visual understanding task with a broad range of vision applications. Despite recent tremendous progress, it remains challenging due to the intrinsic long-tailed class distribution and large intra-class variation. To address these issues, we introduce a novel confidence-aware bipartite graph neural network with adaptive message propagation mechanism for unbiased scene graph generation. In addition, we propose an efficient bi-level data resampling strategy to alleviate the imbalanced data distribution problem in training our graph network. Our approach achieves superior or competitive performance over previous methods on several challenging datasets, including Visual Genome, Open Images V4/V6, demonstrating its effectiveness and generality.

cs.CV↗

arXiv2021

Distribution Alignment: A Unified Framework for Long-tail Visual Recognition

Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the two-stage learning framework via ablative study. Motivated by our discovery, we propose a unified distribution alignment strategy for long-tail visual recognition. Specifically, we develop an adaptive calibration function that enables us to adjust the classification scores for each data point. We then introduce a generalized re-weight method in the two-stage learning to balance the class prior, which provides a flexible and unified solution to diverse scenarios in visual recognition tasks. We validate our method by extensive experiments on four tasks, including image classification, semantic segmentation, object detection, and instance segmentation. Our approach achieves the state-of-the-art results across all four recognition tasks with a simple and unified framework. The code and models will be made publicly available at: https://github.com/Megvii-BaseDetection/DisAlign

cs.CV↗

arXiv2021

An Efficient Hypergraph Approach to Robust Point Cloud Resampling

Efficient processing and feature extraction of largescale point clouds are important in related computer vision and cyber-physical systems. This work investigates point cloud resampling based on hypergraph signal processing (HGSP) to better explore the underlying relationship among different cloud points and to extract contour-enhanced features. Specifically, we design hypergraph spectral filters to capture multi-lateral interactions among the signal nodes of point clouds and to better preserve their surface outlines. Without the need and the computation to first construct the underlying hypergraph, our low complexity approach directly estimates hypergraph spectrum of point clouds by leveraging hypergraph stationary processes from the observed 3D coordinates. Evaluating the proposed resampling methods with several metrics, our test results validate the high efficacy of hypergraph characterization of point clouds and demonstrate the robustness of hypergraph-based resampling under noisy observations.

cs.CV↗

arXiv2020

Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language

We address the problem of retrieving a specific moment from an untrimmed video by a query sentence. This is a challenging problem because a target moment may take place in relations to other temporal moments in the untrimmed video. Existing methods cannot tackle this challenge well since they consider temporal moments individually and neglect the temporal dependencies. In this paper, we model the temporal relations between video moments by a two-dimensional map, where one dimension indicates the starting time of a moment and the other indicates the end time. This 2D temporal map can cover diverse video moments with different lengths, while representing their adjacent relations. Based on the 2D map, we propose a Temporal Adjacent Network (2D-TAN), a single-shot framework for moment localization. It is capable of encoding the adjacent temporal relation, while learning discriminative features for matching video moments with referring expressions. We evaluate the proposed 2D-TAN on three challenging benchmarks, i.e., Charades-STA, ActivityNet Captions, and TACoS, where our 2D-TAN outperforms the state-of-the-art.

cs.CV↗