Search Results for author:
Found 21 papers, 9 papers with code
VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
Recent advancements in text-to-video (T2V) diffusion models have enabled high-fidelity and realistic video synthesis.
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model.
Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances
To our best knowledge, Point2RBox-v2 is the first approach to explore the spatial layout among instances for learning point-supervised OOD.
Motion Control for Enhanced Complex Action Video Generation
Furthermore, MVideo supports motion condition editing and composition, facilitating the generation of videos with more complex actions.
Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation
In this paper, we put forth a novel formulation of the aerial object detection problem, namely open-vocabulary aerial object detection (OVAD), which can detect objects beyond training categories without costly collecting new labeled data.
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
These methods typically include an encoder accepting visible patches (normalized) and corresponding patch centers (position) as input, with the decoder accepting the output of the encoder and the centers (position) of the masked parts to reconstruct each point in the masked patches.
ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
We propose a novel text-to-video (T2V) generation benchmark, ChronoMagic-Bench, to evaluate the temporal and metamorphic capabilities of the T2V models (e. g. Sora and Lumiere) in time-lapse video generation.
Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach
At inference, we generate images with arbitrary expansion multiples by inputting an anchor image and its corresponding positional embeddings.
GMTR: Graph Matching Transformers
Meanwhile, on Pascal VOC, QueryTrans improves the accuracy of NGMv2 from $80. 1\%$ to $\mathbf{83. 3\%}$, and BBGM from $79. 0\%$ to $\mathbf{84. 5\%}$.
Ranked #1 on
Graph Matching
on PASCAL VOC
(matching accuracy metric)
HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
To further capture human characteristics, we propose a structure-invariant alignment loss that enforces different masked views, guided by the human part prior, to be closely aligned for the same image.
On the Evaluation and Refinement of Vision-Language Instruction Tuning Datasets
Instead of evaluating the models directly, in this paper, we try to evaluate the Vision-Language Instruction-Tuning (VLIT) datasets.
RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension
To this end, we propose to extract features corresponding to regional objects as soft prompts for LLM, which provides a straightforward and scalable approach and eliminates the need for LLM fine-tuning.
Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning
On classification tasks, for ViT-S, ADCLR achieves 77. 5% top-1 accuracy on ImageNet with linear probing, outperforming our baseline (DINO) without our devised techniques as plug-in, by 0. 5%.
Localized Contrastive Learning on Graphs
Contrastive learning methods based on InfoNCE loss are popular in node representation learning tasks on graph-structured data.
DOTIN: Dropping Task-Irrelevant Nodes for GNNs
Scalability is an important consideration for deep graph neural networks.
Align Representations With Base: A New Approach to Self-Supervised Learning
Existing symmetric contrastive learning methods suffer from collapses (complete and dimensional) or quadratic complexity of objectives.
ESCo: Towards Provably Effective and Scalable Contrastive Representation Learning
In this paper, we propose ESCo (Effective and Scalable Contrastive), a new contrastive framework which is essentially an instantiation of the Information Bottleneck principle under self-supervised learning settings.
Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning
The proposed two methods (FCL, ICL) can be combined synthetically, called Zero-CL, where ``Zero'' means negative samples are \textbf{zero} relevant, which allows Zero-CL to completely discard negative pairs i. e., with \textbf{zero} negative samples.
$m$-mix: Generating hard negatives via multiple samples mixing for contrastive learning
Negative pairs are essential in contrastive learning, which plays the role of avoiding degenerate solutions.
Self-supervised representation learning via adaptive hard-positive mining
Despite their success in perception over the last decade, deep neural networks are also known ravenous to labeled data for training, which limits their applicability to real-world problems.
The Diversified Ensemble Neural Network
Ensemble is a general way of improving the accuracy and stability of learning models, especially for the generalization ability on small datasets.
