Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks117 from public data
- Network representation learning with rich text information1,122
By proving that DeepWalk, a state-of-the-art network representation method, is actually equivalent to matrix factorization (MF), this work proposes text-associated DeepWalk (TADW), which incorporates text features of vertices into network representation learning under the framework of Matrix factorization.
- In-Domain GAN Inversion for Real Image Editing697
An in-domain GAN inversion approach, which not only faithfully reconstructs the input image but also ensures the inverted code to be semantically meaningful for editing, which achieves satisfying real image reconstruction and facilitates various image editing tasks, significantly outperforming start-of-the-arts.
- AnyDoor: Zero-shot Object-level Image Customization539
This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations with desired shapes, and proposes to borrow knowledge from video datasets, which can observe various forms of a single object, leading to stronger model generalizability and robustness.
- Notice of Removal: VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation442
This work presents a decomposed diffusion process via resolving the per-frame noise into a base noise that is shared among all frames and a residual noise that varies along the time axis, which surpasses both GAN-based and diffusion-based alternatives in high-quality video generation.
- Composer: Creative and Controllable Image Synthesis with Composable Conditions404
This work offers a new generation paradigm that allows flexible control of the output image, such as spatial layout and palette, while maintaining the synthesis quality and model creativity, and serves as a general framework and facilitates a wide range of classical generative tasks without retraining.
- Linear local tangent space alignment and application to face recognition267
Since images of faces often belong to a manifold of intrinsically low dimension, the LLTSA algorithm for effective face manifold learning and recognition is developed, which achieves much higher recognition rates than a few competing methods.
- Graph Degree Linkage: Agglomerative Clustering on a Directed Graph179
This paper proposes a simple but effective graph-based agglomerative algorithm, for clustering high-dimensional data, and defines the affinity measure of clusters via the product of average indegree and average outdegree.
- Agglomerative clustering via maximum incremental path integral128
A novel graph-structural agglomerative clustering algorithm, where the graph encodes local structures of data and the affinity between two clusters is defined as Incremental Path Integral, which can be computed in a closed-form exact solution, with linear time complexity with respect to the maximum size of clusters.
- DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning110
A novel algorithm for learning local exposures with deep reinforcement adversarial learning is developed that is superior to state-of-the-art methods in terms of quantitative accuracy and visual illustration.
- CLIP-guided Prototype Modulating for Few-shot Action Recognition106
This work presents a CLIP-guided prototype modulating framework called CLIP-FSAR, which consists of two key components: a video-text contrastive objective and a prototype modulation that bridges the task discrepancy between CLIP and the few-shot video task by contrasting videos and corresponding class text descriptions.
- MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition101
A Motion-augmented Long-short Contrastive Learning (MoLo) method that contains two crucial components, including a long-short contrastive objective and a motion autodecoder, that can simultaneously learn long-range temporal context and motion cues for comprehensive few-shot matching.
- A survey of geometric graph neural networks: data structures, models and applications97
This paper formalizes geometric graph as the data structure, on top of which it provides a unified view of existing models from the geometric message passing perspective, and summarizes the applications as well as the related datasets to facilitate later research for methodology development and experimental evaluation.
- VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM93
The VideoRefer Suite is introduced to empower Video LLM for finer-level spatial-temporal video understanding, i.e., enabling perception and reasoning on any objects throughout the video, and comprehensively assess the spatial-temporal understanding capability of a Video LLM.
- RLIPv2: Fast Scaling of Relational Language-Image Pre-training77
RLIPv2 is proposed, a fast converging model that enables the scaling of relational pre-training to large-scale pseudo-labelled scene graph data and introduces Asymmetric Language-Image Fusion (ALIF), a mechanism that facilitates earlier and deeper gated cross-modal fusion with sparsified language encoding layers.
- Scalable Gaussian process regression using deep neural networks71
A scalable Gaussian process model for regression by applying a deep neural network as the feature-mapping function, which can learn much more meaningful representation of the data by the finite-dimensional but deep-layered feature- mapping function.
- 68
- Distant Supervision for Relation Extraction with Matrix Completion65
Experiments on two widely used datasets with different dimensions of textual features demonstrate that the low-rank matrix completion approach significantly outperforms the baseline and the state-of-the-art methods.
- Recognizing an Action Using Its Name: A Knowledge-Based Approach64
This paper proposes an algorithm, namely adaptive multi-model rank-preserving mapping (AMRM), to train a classifier for action recognition, which is able to evaluate the relatedness of each video in the analogy pool adaptively, and has better capability to bridge the gap between visual features and the semantic information inferred from the ontology.
- 63
- 62
- 57
- Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning48
DiST is presented, which disentangles the learning of spatial and temporal aspects of videos by using a dual-encoder structure, where a pre-trained foundation model acts as the spatial encoder, and a lightweight network is introduced as the temporal encoder.
- Cyclizing Clusters via Zeta Function of a Graph47
An algorithm named Zeta l-links (Zell) is developed which consists of two parts: Zeta merging with a similarity graph and an initial set of small clusters derived from local l- links of samples, to structurize a cluster using cycles in the associated subgraph.
- 44
- LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis30
An easy-to-use regularizer for GAN training, which helps explicitly link some axes of the latent space to a set of pixels in the synthesized image, which can improve the spatial controllability of both 2D and 3D-aware GAN models, barely sacrificing the synthesis performance.
- 27
- 27
- 24
- Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers22
Babel is introduced, an open multilingual LLM that covers the top 25 languages by number of speakers, supports over 90% of the global population, and includes many languages neglected by other open multilingual LLMs and sets a new standard for open multilingual LLMs.
- 22
- 20
- 19
- 19
- Lingshu: Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning17
This work proposes a comprehensive data-curation procedure that efficiently acquires rich medical knowledge data not only from medical imaging but also from extensive medical texts and general domain data and develops a medical-specialized MLLM, Lingshu-Med, which consistently outperforms existing multimodal baselines in most tasks.
- 17
- 16
- 15
- 14
- In-Domain GAN Inversion for Faithful Reconstruction and Editability14
In-domain GAN inversion is proposed, which consists of a domain-guided encoder and a domain-regularized optimizer, to regularize the inverted code in the native latent space of the pre-trained GAN model, to sufficiently reuse the knowledge learned by GANs for image reconstruction, facilitating a wide range of editing applications without any retraining.
- 14
- 14
- 14
- 13
- 12
- 11
- 11
- 10
- 10
- 10
- 9
- 8
- 8
- 8
- 7
- 7
- 7
- 6
- 6
- 6
- 5
- 5
- 5
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- One Path to Model Them All: Learnable-Time Flow Matching for Crystal Structure and Energy Prediction–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.