Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks143 from public data
- 1,399
- 1,300
- Learning Spatio-Temporal Transformer for Visual Tracking1,225
A new tracking architecture with an encoder-decoder transformer as the key component, which models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder learns a query embedding to predict the spatial positions of the target objects.
- 1,004
- Learning Texture Transformer Network for Image Super-Resolution965
A novel Texture Transformer Network for Image Super-Resolution (TTSR), in which the LR and Ref images are formulated as queries and keys in a transformer, respectively, which achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations.
- 943
- Ocean: Object-Aware Anchor-Free Tracking841
This paper introduces a feature alignment module to learn an object-aware feature from predicted bounding boxes that can further contribute to the classification of target objects and background and presents a novel tracking framework based on the anchor-free model.
- Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language640
A Temporal Adjacent Network (2D-TAN) is proposed, a single-shot framework for moment localization that is capable of encoding the adjacent temporal relation, while learning discriminative features for matching video moments with referring expressions.
- Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting500
This paper proposes a Pyramid-context Encoder Network for image inpainting by deep generative models, built upon a U-Net structure with three tailored components, ie.
- 496
- Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition488
TASN consists of a trilinear attention module, which generates attention maps by modeling the inter-channel relationships, an attention-based sampler which highlights attended parts with high resolution, and a feature distiller, which distills part features into an object-level feature by weight sharing and feature preserving strategies.
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation484
A new advanced VLA architecture derived from VLM that has a specialized action module conditioned on VLM output is presented that not only significantly surpasses existing VLAs in task performance and but also exhibits remarkable adaptation to new robots and generalization to unseen objects and backgrounds.
- Rethinking and Improving Relative Position Encoding for Vision Transformer467
New relative position encoding methods dedicated to 2D images, called image RPE (iRPE), are proposed, which consider directional relative distance modeling as well as the interactions between queries and relative position embeddings in self-attention mechanism.
- 423
- AutoFormer: Searching Transformers for Visual Recognition366
This work proposes a new one-shot architecture search framework, namely AutoFormer, dedicated to vision transformer search, which surpass the recent state-of-the-arts such as ViT and DeiT and achieves top-1 accuracy on ImageNet.
- Learning Joint Spatial-Temporal Transformations for Video Inpainting365
This paper simultaneously fill missing regions in all input frames by self-attention, and proposes to optimize STTN by a spatial-temporal adversarial loss to show the superiority of the proposed model.
- The Eighth Visual Object Tracking VOT2020 Challenge Results350
A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in theVDT challenges.
- MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation337
The first joint audio-video generation framework that brings engaging watching and listening experiences simultaneously, towards high-quality realistic videos is proposed, with a novel Multi-Modal Diffusion model with two-coupled denoising autoencoders.
- 323
- Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning318
This paper proposes SOHO to "Seeing Out of tHe bOx" that takes a whole image as input, and learns vision-language representation in an end-to-end manner, and does not require bounding box annotations which enables inference 10 times faster than region-based approaches.
- Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions293
A novel High-resolution and Diversified VIdeo-LAnguage pre-training model (HD-VILA) for many visual tasks that outperform SOTA models with relative increases and achieves new state-of-the-art results in 10 VL understanding tasks and 2 more novel text-to-visual generation tasks.
- LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search265
This work presents LightTrack, which uses neural architecture search (NAS) to design more lightweight and efficient object trackers that achieve superior performance compared to handcrafted SOTA trackers, such as SiamRPN++ and Ocean, while using much fewer model Flops and parameters.
- 257
- 230
- Revisiting Anchor Mechanisms for Temporal Action Localization215
A novel anchor-free action localization module that represents an action instance as a point with its distances to the starting boundary and ending boundary, alleviating the pre-defined anchor restrictions in terms of action localization and duration is proposed.
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors201
This paper proposes a new zero-reference low-light enhancement framework trainable solely with normal light images, and devise an illumination-invariant prior inspired by the theory of physical light transfer that serves as the bridge between normal and low-light images.
- MiniViT: Compressing Vision Transformers with Weight Multiplexing186
MiniViT, a new compression framework, which achieves parameter reduction in vision transformers while retaining the same performance, and makes the weights shared across layers, while imposing a transformation on the weights to increase diversity.
- Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation180
A novel approach that strengthens the interaction between spatial and temporal perceptions is proposed, utilizing a swapped cross-attention mechanism in 3D windows that alternates the “query” role between spatial and temporal blocks, enabling mutual reinforcement for each other.
- AI Coach: Deep Human Pose Estimation and Analysis for Personalized Athletic Training Assistance166
This paper proposes to create an AI coach system to provide personalized athletic training experiences with several distinct features, and shows that the proposed system can lead to a remarkably better user training experience by extensive user studies.
- WSOD2: Learning Bottom-Up and Top-Down Objectness Distillation for Weakly-Supervised Object Detection166
This paper proposes a novel WSOD framework with Objectness Distillation (i.e., WSOD2) by designing a tailored training mechanism for weakly-supervised object detection, and explores different adaptive training curves for BU/TD objectness, and shows that the proposedWSOD2 can achieve state-of-the-art results.
- DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks161
A novel framework for instance-level image translation by Deep Attention GAN (DA-GAN), which enables DA-GAN to decompose the task of translating samples from two sets into translating instances in a highly-structured latent space.
- CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment159
This paper proposes a Om-nisource Cross-modal Learning method equipped with a Video Proxy mechanism on the basis of CLIP, namely CLIP-ViP, and shows that this approach improves the performance of CLIP on video-text retrieval by a large margin.
- Show, Adapt and Tell: Adversarial Training of Cross-Domain Image Captioner158
A novel adversarial training procedure to leverage unpaired data in the target domain and a novel critic-based planning method to select high-quality sentences without additional supervision is proposed.
- Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting153
First, a patch-level density map is extracted by a density estimation model and further grouped into several density levels which are determined over full datasets, which can significantly condense the density distribution into several clusters, and enable that the density variance can be learned by a single model.
- 136
- Learning Trajectory-Aware Transformer for Video Super-Resolution124
A novel Trajectory-aware Transformer for Video Super-Resolution (TTVSR) is proposed, which formulate video frames into several pre-aligned trajectories which consist of continuous visual tokens that enable Transformers to model long-range features.
- What Dress Fits Me Best?112
The experimental results demonstrate the superiority of the first framework for learning the compatibility of clothing styles and body shapes from social big data, with the goal to recommend a user about what to wear better in relation to his/her essential body attributes.
- Beyond Narrative Description84
This paper forms the task of poem generation into two correlated sub-tasks by multi-adversarial training via policy gradient, through which the cross-modal relevance and poetic language style can be ensured.
- Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training (Best Paper Award)84
This paper forms the task of poem generation into two correlated sub-tasks by multi-adversarial training via policy gradient, through which the cross-modal relevance and poetic language style can be ensured.
- Unified Multi-Modal Latent Diffusion for Joint Subject and Text Conditional Image Generation81
This work presents a novel Unified Multi-Modal Latent Latent Diffusion (UMM-Diffusion) which takes joint texts and images containing specified subjects as input sequences and generates customized images with the subjects.
- Domain-Aware Universal Style Transfer80
A unified architecture, Domain-aware Style Transfer Networks (DSTN) that transfer not only the style but also the property of domain from a given reference image, and designs a novel domainness indicator that captures the domainness value from the texture and structural features of reference images.
- Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment77
This paper proposes a practical solution named degraded-reference IQA (DR-IQA), which exploits the inputs of IR models, degraded images, as references to extract reference information from degraded images by distilling knowledge from pristine-quality images.
- 76
- Multi-Scale 2D Temporal Adjacency Networks for Moment Localization With Natural Language75
A Multi-Scale Temporal Adjacency Network (MS-2D-TAN), a single-shot framework for moment localization capable of encoding the adjacent temporal contexts at each scale, while learning discriminative features for matching video moments with referring expressions is proposed.
- MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images72
MovieFactory, the first fully automated movie generation model to the best of the authors' knowledge, empowers users to create captivating movies with smooth transitions using simple text inputs, surpassing existing methods that produce soundless videos limited to a single scene of modest quality.
- Deep Attention Neural Tensor Network for Visual Question Answering70
A novel deep attention neural tensor network (DA-NTN) for visual question answering, which can discover the joint correlations over images, questions and answers with tensor-based representations and integrates into the state-of-the-art VQA models.
- Let Your Photos Talk: Generating Narrative Paragraph for Photo Stream via Bidirectional Attention Recurrent Neural Networks68
This paper proposes a novel joint learning model that can attend on the discovered semantic relation to produce a sentence sequence and maintain its consistence with the photo stream and integrates the two-step learning components into one single optimization formulation and train the network in an end-to-end manner.
- 360-Indoor: Towards Learning Real-World Objects in 360° Indoor Equirectangular Images66
A real-world 360° panoramic object detection dataset, 360-Indoor, which is a new benchmark for visual object detection and class recognition in 360° indoor images and has several distinct properties, including the largest category number and the most complete annotations on average.
- Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions64
This work proposes to break up the end-to-end VQA into two steps: explaining and reasoning, in an attempt towards a more explainable VZA by shedding light on the intermediate results between these two steps.
- Cyclic Differentiable Architecture Search62
This work proposes new joint optimization objectives and a novel Cyclic Differentiable ARchiTecture Search framework, dubbed CDARTS, which enables the evolution of the architecture to fit the final evaluation network.
- 4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement58
A novel learnable context-aware 4-dimensional lookup table (4D LUT) is proposed, which achieves content-dependent enhancement of different contents in each image via adaptively learning of photo context, and outperforms other state-of-the-art methods in widely-used benchmarks.
- Show, Reward and Tell: Automatic Generation of Narrative Paragraph From Photo Stream by Adversarial Training58
This paper proposes a sequence-to-sequence modeling approach with reinforcement learning and adversarial training for the creation of narrative paragraph for a photo stream, and proposes a hierarchical recurrent neural network as story generator, optimized by reinforcement learning with rewards.
- Efficient Clothing Retrieval with Semantic-Preserving Visual Phrases58
Experiments and comparisons indicate that the SPVP significantly enhances the discriminative power of local features with a slight increase of memory usage or runtime consumption compared to the BOW model.
- NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results54
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results and gauges the state-of-the-art in single image super- resolution.
- Reference-Based Defect Detection Network53
A Reference-based Defect Detection Network (RDDN) is proposed, which proposes to leverage the carried context information of context reference, which is the concentric bigger box of each region proposal, to perform more accurate region classification and regression.
- DGCN: Dynamic Graph Convolutional Network for Efficient Multi-Person Pose Estimation53
This paper proposes a novel Dynamic Graph Convolutional Module (DGCM), which takes into account all relations and construct dynamic graphs to tolerate large variations of human pose and achieves relative gains over state-of-the-art bottom-up methods on COCO keypoints and MPII dataset.
- 52
- 50
- Advances in deep learning approaches for image tagging49
The purpose of this paper is to categorize and evaluate different image tagging approaches based on deep learning techniques, including data collection, evaluation metrics, and existing commercial systems, and conclude the advantages of different image tags paradigms.
- 47
- 46
- Aesthetic-Aware Image Style Transfer43
A novel Aesthetic-Aware Model-Optimisation-Based Style Transfer (AAMOBST) model, which can decide colour and texture features separately and is able to keep one of them fixed while changing the other one, which is not applicable for previous methods.
- 41
- 37
- Neural Storyboard Artist36
A novel inspire-and-create framework with a story-to-image retriever that selects relevant cinematic images for inspiration and a storyboard creator that further refines and renders images to improve the relevancy and visual consistency is proposed.
- 35
- 35
- Tagging Personal Photos with Transfer Deep Learning35
An ontology consisting of a hierarchical vocabulary tailored for personal photos is designed, to solve the semantic distribution gap and discover the intermediate image representations and ontology priors by deep learning with bottom-up and top-down transfers across two domains.
- AlphaBlock: Embodied Finetuning for Vision-Language Reasoning in Robot Manipulation34
A novel framework for learning high-level cognitive capabilities in robot manipulation tasks, such as making a smiley face using building blocks is proposed, and a closed-loop multi-modal embodied planning model that autoregressively generates plans by taking image observations as input is proposed.
- 34
- 32
- 31
- Transferring Foundation Models for Generalizable Robotic Manipulation29
A novel paradigm that effectively leverages language-reasoning segmentation mask generated by internet-scale foundation models, to condition robot manipulation tasks, and develops a two-stream 2D policy model based on imitation learning, which processes raw images and object masks to predict robot actions with a local-global perception manner.
- TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation29
A novel Trajectory-aware Transformer for Video Frame Interpolation (TTVFI) is proposed, which formulate the warped features with inconsistent motions as query tokens, and formulate relevant regions in a motion trajectory from two original consecutive frames into keys and values.
- Multi-source Multi-level Attention Networks for Visual Question Answering29
This work proposes multi-source multi-level attention networks for visual question answering that can benefit both spatial inferences by visual attention on context-aware region representation and reasoning by semantic attention on concepts as well as external knowledge.
- 29
- One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking28
This paper proposes a one-shot neural ensemble architecture search (NEAS) solution that addresses the two challenges of enlarged search space and potentially more complexity for the searched model, and introduces a novel diversity-based metric to guide search space shrinking.
- Spatiotemporal Predictive Pre-training for Robotic Motor Control27
A simple yet effective visual pre-training framework termed as STP for robotic motor control is presented, which jointly performs spatial and temporal prediction with different masking ratios and a dual-decoder design by utilizing large-scale egocentric video data.
- 22
- Emotion Reinforced Visual Storytelling22
This paper introduces the concept of emotion engaged in visual storytelling, and introduces the proposed model, which is able to generate stories based on not only emotions generated by the novel emotion generator, but also customized emotions.
- Self-View Grounding Given a Narrated 360° Video22
This project proposes a novel Visual Grounding Model (VGM) to implicitly and efficiently predict the NFoVs given the video content and subtitles and achieves state-of-the-art NFoV-grounding performance.
- Meta Attention-Generation Network for Cross-Granularity Few-Shot Learning20
This paper proposes a novel learning problem called cross-granularity few-shot learning (CG-FSL), where sufficient samples of coarse-grained classes are available for training, but in the test stage, the goal is to classify the fine- grained subclasses.
- Language-Guided Face Animation by Recurrent StyleGAN-Based Generator19
A recurrent motion generator to extract a series of semantic and motion information from the language and feed it along with visual information to a pre-trained StyleGAN to generate high-quality frames to animate a static face image with the help of languages.
- 18
- Learning Semantic-aware Normalization for Generative Adversarial Networks18
This paper proposes a novel image synthesis approach by learning adversarial training, a channel grouping loss, and a mutual information loss for joint optimization, which not only enables high-fidelity image synthesis but leads to superior interpretable properties.
- From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots18
This work proposes a progressive learning approach for image-pivoted zero-resource machine translation, where words are less diverse when grounded in the image, and then progress to learn the sentence-level translation by utilizing the learned word translation to suppress noises in image- pivoted multi-lingual sentences.
- Learning Profitable NFT Image Diffusions via Multiple Visual-Policy Guided Reinforcement Learning16
Extensive experiments including objective evaluations and user studies demonstrate that the proposed Diffusion-MVP framework can generate NFT images showing more visually engaging elements and higher market value, compared with state-of-the-art approaches.
- 16
- Effective logo retrieval with adaptive local feature selection14
A novel approach to extract and combine local features for effective logo retrieval by developing a strategy of adaptive feature selection by a weight updating mechanism is proposed.
- 3D Object Retrieval with Multimodal Views13
The evaluation results show a promising scenario about multimodal view-based 3D retrieval methods, and reveal interesting insights in dealing with multi-modal data.
- Applying Median Filtering with Artificial Color13
The purpose of this article is to introduce and study the effects of neighborhood operations in Artificial Color.
- Recent advances in chemodynamic nanotherapeutics to overcome multidrug resistance in cancers12
A comprehensive overview of CDT-based strategies in cancer treatment is provided, highlighting developments of CDT and CDT-based combination strategies in tumor therapy, especially in overcoming MDR challenges.
- AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation12
A Prompt-based Cross-Modal Generation Framework (PCM-Frame) to leverage two powerful pre-trained models, including CLIP and StyleGAN, and conducts a user study to demonstrate its superiority over the competing methods of text-to-image translation with complicated semantics.
- 12
- Learning Fine-Grained Motion Embedding for Landscape Animation12
A model named FGLA is proposed to generate high-quality and realistic videos by learning Fine-Grained motion embedding for Landscape Animation to generate time-lapse videos from a single landscape image.
- Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution11
The quality of SR results sampled by the proposed method with fewer steps outperforms the quality of results sampling by current methods with randomness from the same pre-trained diffusion-based SR model, which means that the sampling method "boosts" current diffusion- based SR models without any additional training.
- Degradation-Guided Meta-Restoration Network for Blind Super-Resolution11
A Degradation-guided Meta-restoration network for blind Super-Resolution (DMSR) that facilitates image restoration for real cases and outperforms SOTA by a large margin on three widely-used benchmarks is proposed.
- Show, Reward, and Tell11
An attribute-based Hierarchical Generative model with Reinforcement Learning and adversarial training and considers the story generator and the reward critic as adversaries, which aims to create indistinguishable paragraphs to human-level stories.
- 11
- SINC: Self-Supervised In-Context Learning for Vision-Language Tasks10
A succinct and general framework, Self-supervised IN-Context learning (SINC), that introduces a meta-model to learn on self-supervised prompts consisting of tailored demonstrations, which outperforms gradient-based methods in various vision-language tasks under few-shot settings.
- Exploiting hierarchical visual features for visual question answering10
It is suggested that the low-level layer features are superior in low- level semantic questions, and a novel VQA model named Hierarchical Feature Network (HFnet) is proposed, which exploits intermediate CNN layers to derive various semantics for VZA.
- 10
- ViCo: Engaging Video Comment Generation with Human Preference Rewards9
This paper proposes ViCo with three novel designs to tackle the challenges for generating engaging Video Comments, and proposes to utilize the number of “likes” each comment receives as a proxy of human preference to quantify the engagement of comments.
- A Picture is Worth a Thousand Words8
This work proposes a unified multi-modal framework that jointly models image-and-text representations with a Transformer network, which supports rich image creation by accepting multiple captions as input and considers the relations among input captions to encourage diversity in training.
- A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation8
This work proposes a unified multi-modal framework that jointly models image-and-text representations with a Transformer network, which supports rich image creation by accepting multiple captions as input and considers the relations among input captions to encourage diversity in training.
- 8
- A novel learning-based switching median filter for suppression of impulse noise in highly corrupted colour images8
The results of experiments have demonstrated that the MS based NFTS (MSN) filter is superior to the support vector machine and neural network for denoising highly corrupted images, in terms of noise suppression and detail preservation.
- Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution7
A multi-scale Vector-Quantized Degradation model for animation video Super-Resolution (VQD-SR) is proposed to decompose the local details from global structures and transfer the degradation priors in real-world animation videos to a learned vector-quantized codebook for degradation modeling.
- MobileVidFactory: Automatic Diffusion-Based Social Media Video Generation for Mobile Devices from Text7
A system to automatically generate vertical mobile videos where users only need to give simple texts mainly, and allows users to add specified screen texts for enriching visual expression, and specify texts for automatic reading with optional voices as they like.
- 7
- 7
- 6
- 6
- What Visual Attributes Characterize an Object Class?6
The approach ensures the learned visual attributes to be visually recognizable and representative, in contrast to manually constructed attributes that contain properties difficult to be visualized, e.g., “smelly,” “smart.”
- 5
- 5
- RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning4
Repainter is a reinforcement learning framework that integrates spatial-matting trajectory refinement with Group Relative Policy Optimization (GRPO) and introduces a composite reward mechanism that balances global, local, and semantic constraints, effectively reducing visual artifacts and reward hacking.
- Exploring Anchor-based Detection for Ego4D Natural Language Query4
The technique report of Ego4D natural language query challenge in CVPR 2022 is provided and the solution of this challenge is proposed to solve the above issues.
- 4
- 4
- Finding logos in real-world images with point-context representation-based region search4
This paper proposes a novel framework for finding visual logos in the real-world images by exploiting the contextual shape and patch information around feature points, merge them into a combined feature representation (point-context).
- Point-context descriptor based region search for logo recognition4
A point-context descriptor for region modeling is adopted, which is a highly correlated integration of three kinds of features: point, shape, and patch, for logo recognition.
- Beyond Success: Refining Elegant Robot Manipulation from Mixed-Quality Data via Just-in-Time Intervention3
A decoupled refinement framework that improves execution quality without modifying or retraining the base VLA policy is developed and the proposed model enables robotic control that values not only whether tasks succeed, but also how they are performed.
- RoLD: Robot Latent Diffusion for Multi-task Policy Modeling3
This study proposes a novel approach that decouples robot action trajectory encoding and control policy generation by leveraging latent action trajectory spaces, enhancing the generalization ability of policy generation on multi-task manipulation tasks.
- Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations3
This work proposes a novel method to find semantic variations of the target text in the CLIP space that achieves a new state-of-the-art on zero-shot GAN adaptation in terms of both diversity and quality.
- 3
- 3
- 3
- Searching Personal Photos on the Phone with Instant Visual Query Suggestion and Joint Text-Image Hashing3
This paper presents an innovative personal photo search system on the phone, which enables instant and accurate photo search by visual query suggestion and joint text-image hashing, and significantly outperforms the existing client-based solutions in terms of search efficiency and precision.
- 2
- A review of load forecasting technology based on artificial intelligence2
This paper discusses the application of different artificial intelligence technologies in power load forecasting by sorting out the development status of related technologies, and provides a reference direction for future research.
- 2
- 2
- 1
- Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution1
A novel Frequency-Transformer (FTVSR) is proposed for handling low-quality videos that carry out self-attention in a combined space-time-frequency domain and it is discovered that a ``divided attention'' which conducts a joint space- frequencies attention before applying temporal-frequency attention, leads to the best video enhancement quality.
- 1
- –
- –
- –
- –
- Capture Concept Through Comparison: Vision-and-Language Representation Learning with Intrinsic Information Mining–
A novel approach to C apture various C oncepts through data C omparison (C3) for learning cross-modal representations through a data mining procedure to uncover intrinsic information within the database, avoiding the need for external annotations.
- –
- MMPT'21: International Joint Workshop on Multi-Modal Pre-Training for Multimedia Understanding–
This workshop aims to gather peer researchers on related topics for more insightful discussion and to attract more researchers to explore and investigate more opportunities of designing and using innovative pre-training models for multimedia tasks.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.