Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks42 from public data
- Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation1,421
A systematic study of the Copy-Paste augmentation for instance segmentation where the authors randomly paste objects onto an image finds that the simple mechanism of pasting objects randomly is good enough and can provide solid gains on top of strong baselines.
- Attentive Generative Adversarial Network for Raindrop Removal from A Single Image841
This paper visually removes raindrops, and thus transforming a raindrop degraded image into a clean one, using an attentive generative network using adversarial training and injects visual attention into both the generative and discriminative networks.
- Spatiotemporal Contrastive Video Representation Learning600
This work proposes a temporally consistent spatial augmentation method to impose strong spatial augmentations on each frame of the video while maintaining the temporal consistency across frames, and proposes a sampling-based temporal augmentation methods to avoid overly enforcing invariance on clips that are distant in time.
- InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output216
A versatile large-vision language model that supports long-contextual input and output, InternLM-XComposer-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend.
- Multiple Sound Sources Localization from Coarse to Fine192
A two-stage audiovisual learning framework that disentangles audio and visual representations of different categories from complex scenes, then performs cross-modal feature alignment in a coarse-to-fine manner achieves state-of-the-art results on public dataset of localization, as well as considerable performance on multi-source sound localization in complex scenes.
- Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation169
This work proposes a novel framework named Hierarchical Audio-to-Gesture (HA2G) for co-speech gesture generation, and develops a contrastive learning strategy based on audio-text alignment for better audio representations.
- ATRW165
A novel method for tiger re-identification is proposed, which introduces precise pose parts modeling in deep neural networks to handle large pose variation of tigers, and reaches notable performance improvement over existing re-ID methods.
- 111
- TA2N: Two-Stage Action Alignment Network for Few-Shot Action Recognition106
A Two-stage Action Alignment Network (TA2N) is addressed sequentially through a temporal affine transform, which warps each video feature to its action duration while dismissing the action-irrelevant feature.
- Weakly Supervised Scene Parsing with Point-Based Distance Metric Learning84
This paper proposes a Point-based Distance Metric Learning (PDML), which leverages semantic relationship among the annotated points by encouraging the feature representations of the intra- and inter-category points to keep consistent.
- Motion-aware Contrastive Video Representation Learning via Foreground-background Merging72
Foreground-background Merging (FAME) is proposed to deliberately compose the moving foreground region of the selected video onto the static background of others to alleviate background bias and achieve the state-of-the-art performance on downstream tasks across UCF101, HMDB51, and Diving48 datasets.
- 68
- Class-Aware Sounding Objects Localization via Audiovisual Correspondence53
A two-stage step-by-step learning framework to localize and recognize sounding objects in complex audiovisual scenarios using only the correspondence between audio and vision, which is superior in localizing and recognizing objects as well as filtering out silent ones.
- Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization43
A multi-level feature optimization framework to improve the generalization and temporal modeling ability of learned video representations and a simple temporal modeling module from multi- level features to enhance motion pattern learning is proposed.
- Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation34
Semanticaware Temporal Accumulation score (STA) is proposed to prune spatiotemporal tokens integrally to optimize the speed-accuracy trade-off and is able to progressively prune the tokens without introducing any additional parameters or requiring further re-training.
- Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision27
This paper designs a region-based pretext task which requires the model to transform instance representations from one view to another, guided by context features, and introduces a simple network design that successfully reconciles the simultaneous learning process of both holistic and local representations.
- Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos26
This work proposes a novel semantic-aware masked slot attention that effectively identifies multiple object instances with semantic structure, reaching promising results on unsupervised video object discovery and achieves state-of-the-art performance on dense label propagation tasks, demonstrating the potential for object-centric analysis.
- Dual Contrastive Learning for Spatio-temporal Representation26
A novel dual contrastive formulation is presented that learns effective spatio-temporal representations and obtains state-of-the-art or comparable performance on UCF-101, HMDB-51, and Diving-48 datasets.
- 24
- Controllable augmentations for video representation learning21
This paper proposes a framework to jointly utilize local clips and global videos to learn from detailed region-level correspondence as well as general long-term temporal relations, and introduces local-global temporal order dependency to further bridge the gap between clip-level and video-level representations for robust temporal modeling.
- Finding Action Tubes with a Sparse-to-Dense Framework18
This paper proposes for the first time, an efficient framework that generates action tube proposals from video streams with a single forward pass in a sparse-to-dense manner and introduces a new dynamic feature sampling module (DTS) to effectively approximate the tube output while keeping the system tractable.
- 16
- 15
- 11
- SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion10
This paper proposes SplatSSC, a novel framework that resolves limitations with a depth-guided initialization strategy and a principled Gaussian aggregator, and develops the Decoupled Gaussian Aggregator (DGA), which enhances robustness by decomposing geometric and semantic predictions during the Gaussian-to-voxel splatting process.
- Renmin University of China and Zhejiang Gongshang University at TRECVID 2019: Learn to Search and Describe Videos.9
This paper combines the classical encoder-decoder model with multi-level video encoding and attribute prediction to enhance the classical encoder-decoder model with multi-level video encoding and attribute prediction in the VTT Description Generation subtask.
- Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation6
- CogStream: Context-guided Streaming Video Question Answering5
This paper introduces a challenging task called Context-guided Streaming Video Reasoning (CogStream), which simulates real-world streaming video scenarios, requiring models to identify the most relevant historical contextual information to deduce answers for questions about the current stream.
- 5
- 3
- TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion2
TGSFormer is proposed, a scalable Temporal Gaussian Splatting framework for embodied SSC, offering superior accuracy and scalability with significantly fewer primitives while maintaining consistent long-term scene integrity.
- 2
- 2
- SimC3D: A Simple Contrastive 3D Pretraining Framework Using RGB Images1
It is empirically demonstrated that the primary benefit of the 2D modality stems from the incorporation of locality information, and SimC3D directly employs 2D positional embeddings as a stronger contrastive objective, eliminating the necessity for 2D backbones and leading to considerable performance improvements.
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. 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.