Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks137 from public data
- Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators896
This paper proposes a low-cost approach (without any training or optimization) by leveraging the power of existing text-to-image synthesis methods, making them suitable for the video domain, and introduces a new task, zero-shot text-to-video generation.
- OneFormer: One Transformer to Rule Universal Image Segmentation653
This work proposes OneFormer, a universal image segmentation framework that unifies segmentation with a multi-task train-once design that outperforms specialized Mask2Former models across all three segmentation tasks on ADE20k, Cityscapes, and COCO.
- Neighborhood Attention Transformer540
NA is a pixel-wise operation, localizing self attention to the nearest neighboring pixels, and therefore enjoys a linear time and space complexity compared to the quadratic complexity of SA, and is the first efficient and scalable sliding window attention mechanism for vision.
- 520
- Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models369
The Forget-Me-Not method is proposed, a model-centric and efficient solution designed to remove identities, objects, or styles from a well-configured text-to-image model in as little as 30 seconds, without significantly impairing its ability to generate other content.
- More Control for Free! Image Synthesis with Semantic Diffusion Guidance354
This work investigates fine-grained, continuous control of the denoising diffusion probabilistic model class, and introduces a novel unified framework for semantic diffusion guidance, which allows either language or image guidance, or both.
- Versatile Diffusion: Text, Images and Variations All in One Diffusion Model295
This work expands the existing single-flow diffusion pipeline into a multi-task multimodal network, dubbed Versatile Diffusion (VD), that handles multiple flows of text-to-image, image- to-text, and variations in one unified model.
- 287
- StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text273
Experiments show that StreamingT2V produces more motion, while competing methods suffer from video stagnation when applied naively in an autoregressive fashion, surpassing competitors in both consistency and motion.
- AlignSeg: Feature-Aligned Segmentation Networks199
This paper proposes Feature-Aligned Segmentation Networks (AlignSeg), a feature aggregation network that adopts a simple learnable interpolation strategy to learn transformation offsets of pixels that can effectively relieve the feature misalignment issue caused by multi-resolution feature aggregation.
- VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution179
This work proposes Video Implicit Neural Representation (VideoINR), and shows its applications for Space-Time Video Super-Resolution, and shows that VideoINR achieves competitive performances with state-of-the-art STVSR methods on common up-sampling scales and significantly outperforms prior works on continuous and out- of-training-distribution scales.
- Cosmos 3: Omnimodal World Models for Physical AI150
This report introduces Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture and demonstrates omnimodal world models as scalable, general-purpose backbones for embodied agents.
- Pyramid Attention Network for Image Restoration142
A novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid, and is designed to be able to borrow clean signals from their “clean” correspondences at the coarser levels.
- 141
- SeMask: Semantically Masked Transformers for Semantic Segmentation132
This paper argues that incorporating semantic information of the image into pretrained hierarchical transformer-based backbones while finetuning improves the performance considerably and proposes SeMask, a simple and effective framework that incorporates semantic information into the encoder with the help of a semantic attention operation.
- Deep learning-based automated image segmentation for concrete petrographic analysis120
The experimental results showed that CNN outperforms the color-based segmentation by a considerable margin, and has comparable accuracy to human experts, and the segmentation time is reduced to mere seconds.
- Adaptive Consistency Regularization for Semi-Supervised Transfer Learning115
This work considers semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm that can utilize both powerful pre-trained models from source domain as well as labeled/unlabeled data in the target domain.
- Towards Layer-wise Image Vectorization114
This work proposes Layer-wise Image Vectorization, namely LIVE, to convert raster images to SVGs and simultaneously maintain its image topology, and demonstrates that LIVE presents more plausible vectorized forms than prior works and can be generalized to new images.
- ConvMLP: Hierarchical Convolutional MLPs for Vision102
Experiments on object detection and semantic segmentation show that visual representation learned by ConvMLP can be seamlessly transferred to downstream tasks and achieve competitive results with fewer parameters.
- OpenBias: Open-Set Bias Detection in Text-to-Image Generative Models97
This paper presents OpenBias, a new pipeline that identifies and quantifies the severity of biases agnostically, without access to any precompiled set, and demonstrates that OpenBias agrees with current closed-set bias detection methods and human judgement.
- Prompt-Free Diffusion: Taking “Text” Out of Text-to-Image Diffusion Models92
The proposed frame-work, Prompt-Free Diffusion, relies on only visual inputs to generate new images and outperform prior exemplar-based image synthesis approaches, and is naturally extensible to other downstream applications such as anime figure generation and virtual try-on, with promising quality.
- HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models87
The Prompt-Aware Introverted Attention layer enhancing self-attention scores by prompt information resulting in better text aligned generations is designed and the Reweighting Attention Score Guidance mechanism seamlessly integrating a post-hoc sampling strategy into the general form of DDIM is introduced.
- Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach86
This work proposes TextSeg, a large-scale fine-annotated text dataset with six types of annotations, and introduces Text Refinement Network (TexRNet), a novel text segmentation approach that adapts to the unique properties of text, e.g. non-convex boundary, diverse texture, etc., which often impose burdens on traditional segmentation models.
- Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand83
A novel inpainting network combining the advantages of the two designs achieves a remarkable visual quality to match state-of-the-art performance in both structure generation and repeating texture synthesis using a single network.
- CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation80
This work proposes a novel comprehensive feature aggregation approach (CompFeat) to refine features at both frame-level and object-level with temporal and spatial context information to eliminate ambiguities introduced by only using single-frame features.
- Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels76
This paper proposes a Study Group Learning (SGL) scheme to improve the robustness of the model trained on noisy labels, and shows that a learned enhancement map provides better visualization than conventional methods as an auxiliary tool for clinicians.
- 74
- AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition72
This work reformulates the training of AdaFocus as a simple one-stage algorithm by introducing a differentiable interpolation-based patch selection operation, enabling efficient end-to-end optimization and presenting an improved training scheme to address the issues introduced by the one- stage formulation.
- 67
- 65
- High-Resolution Deep Image Matting64
The proposed HDMatt approach runs matting in a patch-based crop-and-stitch manner for high-resolution inputs with a novel module design to address the contextual dependency and consistency issues between different patches.
- 52
- 41
- Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimation41
This paper predicts and fuse a pyramid of motion fields from multiple scales of feature representations to generate a more refined motion field and uses a novel cyclic teacher-student training strategy to make the inference end-to-end and further improve the tracking performance.
- Object Localization under Single Coarse Point Supervision39
A coarse point refinement (CPR) approach, which to the best knowledge is the first attempt to alleviate semantic variance from the perspective of algorithm, which ensures training high-performance object localizer under coarse point supervision.
- 38
- Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids.38
This study proposes a recurrent feature-pyramid structure to squeeze rich spatial and semantic features into a single prediction layer that further reduces the number of parameters to learn, and is the best performed model of learning object detection from scratch.
- FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude35
The end-to-end design, development and evaluation of FarSight, an innovative software system designed for whole-body biometric recognition that combines the physics of imaging and deep learning models to enhance image restoration and biometric feature encoding are presented.
- VMFormer: End-to-End Video Matting with Transformer35
VMFormer is proposed: a transformer-based end-to-end method for video matting that leverages self-attention layers to build global integration of feature sequences with short-range temporal modeling on successive frames and outperforms previous CNN-based video matting methods on synthetic benchmarks.
- 34
- The 1st Tiny Object Detection Challenge: Methods and Results33
A brief summary of the 1st Tiny Object Detection (TOD) Challenge is provided including brief introductions to the top three methods.
- Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection31
PseudoIntersection-over-Union (PSEudo-IoU): a simple metric that brings more standardized and accurate assignment rule into anchor-free object detection frameworks without any additional computational cost or extra parameters for training and testing, making it possible to further improve anchor- free object detection.
- 30
- 30
- 30
- 29
- 28
- 28
- Understanding and Accelerating Neural Architecture Search With Training-Free and Theory-Grounded Metrics27
This work designs a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation, and presents a unified framework to understand and accelerate NAS by disentangling “TEG” characteristics of searched networks – Trainability, Expressivity, Generalization – all assessed in a training-free manner.
- 26
- 26
- Efficient Image Generation with Variadic Attention Heads25
This work proposes a simple, yet powerful method to reduce trade-offs: allow the attention heads of a single transformer to attend to multiple receptive fields in a Neighborhood Attention architecture for image generation.
- 25
- 25
- 24
- 24
- 23
- 22
- 22
- VASE: Object-Centric Appearance and Shape Manipulation of Real Videos21
This work introduces a framework that is object-centric and is designed to control both the object's appearance and, notably, to execute precise and explicit structural modifications on the object.
- 20
- 19
- 18
- Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait16
FarSight is proposed, a unified end-to-end system for person recognition that integrates complementary biometric cues across face, gait, and body shape modalities and was evaluated in the 2025 NIST RTE Face in Video Evaluation (FIVE), which conducts standardized face recognition testing on the BRIAR dataset.
- 16
- 16
- 15
- Grounded-Instruct-Pix2Pix: Improving Instruction Based Image Editing with Automatic Target Grounding15
- 15
- CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting14
This paper introduces the GS Tokenizer to generate serialized gaussian tokens, which are then processed through transformer layers pre-initialized with weights from point cloud models, resulting in the 3DGS embeddings, and introduces an image voting loss to guide the directionality and convergence of gradient optimization.
- 14
- 13
- 12
- 12
- 10
- ReCoRo: Re gion- Co ntrollable Ro bust Light Enhancement with User-Specified Imprecise Masks10
Region-Controllable Robust Light Enhancement (ReCoRo), a novel framework that allows users to directly specify "where" and "how much" they want to enhance from an input low-light image; meanwhile, the model will learn to intelligently maintain the overall consistent visual appearance and plausible composition via a discriminator.
- Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community9
This work pioneers a paradigm shift, unveiling Social Reward - an innovative reward modeling framework that leverages implicit feedback from social network users engaged in creative editing of generated images, and utilizes Social Reward to fine-tune text-to-image models, yielding images that are more favored by not only Social Reward, but also other established metrics.
- 8
- 8
- 8
- 7
- 7
- 7
- 6
- 6
- Revisiting Pre-training: An Efficient Training Method for Image Classification6
This work proposes to continually repeat a Drop-and-Pick (DaP) learning strategy, which can be leveraged to train classification networks in a more efficient way and is equipped with strong knowledge transferability when used for downstream tasks, especially for hard cases.
- 5
- 5
- Reference-based Painterly Inpainting via Diffusion: Crossing the Wild Reference Domain Gap5
A novel diffusion framework to ``inpaint more wildly'' by taking such references with large domain gaps, built with an image-conditioned diffusion model and introduced with a ladder-side branch and a masked fusion mechanism to work with the inpainting mask.
- 4
- Learning Trimaps via Clicks for Image Matting4
This work introduces Click2Trimap, an interactive model that is capable of predicting high-quality trimaps and alpha mattes with minimal user click inputs and proposes a powerful iterative three-class training strategy and a dedicated simulation function, making Click2Trimap exhibit versatility across various scenarios.
- 4
- 4
- 4
- 4
- One Shot Domain Adaptation for Person Re-Identification4
This work introduces a similarity-guided strategy to progressively assign pseudo labels to unlabeled instances with different confidence scores, which are in turn leveraged as weights to guide the optimization as training goes on and makes significant improvement in the domain adaptation tasks of re-ID.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN2
This paper hypothesize and demonstrate that a series of meaningful, natural, and versatile small, local movements (referred to as"micromotion", such as expression, head movement, and aging effect) can be represented in low-rank spaces extracted from the latent space of a conventionally pre-trained StyleGAN-v2 model for face generation, with the guidance of proper"anchors" in the form of either short text or video clips.
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- MUSE: Illustrating Textual Attributes by Portrait Generation.–
A novel approach, MUSE, to illustrate textual attributes visually via portrait generation by extending an image-to-image generative model to accept textual attributes and proposes a new attribute reconstruction metric to evaluate whether the generated portraits preserve the subject's attributes.
- –
- –
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 2026-10-13. 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.