- 博客(130)
- 收藏
- 关注
RSS订阅
原创 coherent motion
Author: ChatGPTCoherent motions refer to patterns of movement that are consistent, structured, and often correlated across space and/or time. The term appears across computer vision, robotics, and human motion analysis, with slightly different but related
2025-07-18 19:16:03
879
原创 Human-Object Interaction (HOI) synthesis
Human-Object Interaction (HOI) synthesis refers to the generation of realistic interactions between humans and objects in virtual or physical environments. Unlike HOI recognition (which focuses on detecting existing interactions), HOI synthesis aims to cre
2025-07-17 19:47:42
524
原创 “显著性”（Saliency）是计算机视觉中的一个重要概念，主要指的是图像或视频中最吸引人注意力的区域或对象
显著性”（Saliency）是计算机视觉中的一个重要概念，主要指的是。它模拟的是人类视觉系统对视觉场景中“显著”区域的感知能力。显著性可以用于图像理解、目标检测、图像压缩、图像分割等多个任务。
2025-07-17 13:54:48
488
原创 Articulated objects are multi-part objects with joints that allow structured movement between parts.
that are。
2025-07-16 17:21:06
453
原创 “Long-horizon” refers to interactions or sequences that unfold over an extended period of time
refers to。
2025-07-14 20:59:27
290
原创 Papers about Anomaly Detection (Reconstruction-based and Restoration-based)
ICCV 2023 Institute of Automation, Chinese Academy of SciencesTargeting for detecting anomalies of various sizes fo rcomplicated normal patterns, we propose a Template-guided Hierarchical Feature Restoration method, which in-troduces two key techniques, b
2023-10-05 15:09:35
995
原创 Online Deep Clustering for Unsupervised Representation Learning
CVPR2020香港中文大学。
2023-06-15 16:50:03
272
原创 Emergent Correspondence from Image Diffusion
Cornell UniversityFinding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explicit supervision. We propose a simple strategy to extract thi
2023-06-10 00:14:50
425
原创 Swin Transformer
Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. Swin transformer: Hierarchical vision transformer using shifted windows. 2021AbtractThis paper presents a new vision Transformer, called Swin Transformer, that cap
2023-02-13 22:45:08
269
原创 小样本分割 高斯过程
Johnander, J., Edstedt, J., Felsberg, M., Khan, F.S., Danelljan, M. (2022). Dense Gaussian Processes for Few-Shot Segmentation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022.Few-shot segme
2023-01-21 09:46:42
257
原创 deep Bayesian learning
https://www.topbots.com/comprehensive-introduction-to-bayesian-deep-learning/NeurIPS 2020The key distinguishing property of a Bayesian approach is marginalization, rather than using a single setting of weights. Bayesian marginalization can particularly im
2022-10-22 17:33:49
226
转载 Ranking loss
相关链接：https://gombru.github.io/2019/04/03/ranking_loss/https://github.com/adambielski/siamese-triplethttps://omoindrot.github.io/triplet-lossPyTorchCosineEmbeddingLoss. It’s a Pairwise Ranking Loss that uses cosine distance as the distance metric. Inp
2022-10-10 11:42:33
222
原创 压缩感知文献阅读
针对正交匹配追踪(OMP)算法在压缩感知理论下的重构效果和所需时间相互矛盾的问题,基于子空间追踪(SP)算法的回溯思想,使用共轭梯度下降算法代替最小二乘法对正交匹配追踪(OMP)算法进行改进.并且对所改进算法的重构精度、重构稳定性进行了仿真实验,结果表明所提算法能保证重构质量良好并且有更好的重构速度和稳定性.马博珩,彭艺. 基于OMP算法的快速压缩感知图像重构[J]. 云南大学学报（自然科学版）,2017,39(2):207-211. DOI:10.7540/j.ynu.20160247.
2022-09-17 20:53:02
334
原创 Anomaly Detection | Metaformer
Paper： Learning Unsupervised Metaformer for Anomaly Detection
2022-03-29 11:42:06
541
原创 anomaly detection dataset/papers/code
https://paperswithcode.com/dataset/mvtecadhttps://paperswithcode.com/dataset/kolektorsdd2
2021-12-06 23:47:20
2300
原创 CV顶会&顶刊
顶会：CVPR,ICCV,ECCV,ICML,NIPS, AAAI, IJCAI,BMVC顶刊：TPAMI, TIP, IJCV, JMLR
2021-12-06 10:31:47
3356
原创 The Correct Way to Measure Inference Time of Deep Neural Networks
https://deci.ai/resources/blog/measure-inference-time-deep-neural-networks/
2021-12-06 09:37:22
311
转载 3. 确定性推理笔记
推理的基本概念3.1.1 推理的定义 3.1.2 推理方式及其分类 1.演绎推理：一般 → 个体 三段论式（三段论法） 2.归纳推理：个体 → 一般 完全归纳推理（必然性推理）不完全归纳推理（非必然性推理） 3.默认推理（缺省推理）：知识不完全的情况下假设某些条件已经具备所进行的推理。 1.确定性推理：推理时所用的知识与证据都是确定的，推出的结论也是确定的，其真值或者为真或者为假。 2.不确定性推理：推理时所用的知识与证据不都是确定的，推出的结论也是不确定的。 1.单调推理（基于经典
2021-11-21 16:47:39
3995
原创 人民日报训练word2vec实验
数据集人民日报：2020年10月04日-2021年10月04日概况25590 articles742362 sentences0.021 billion words294730 tokens182004942 pairs (window size: 5)词云(120 words)训练参数vector dimension: 100window size: 5K: 5batch size: 50epoch: 10learning rate: 0.025训练结果
2021-11-16 08:56:33
722
2
原创 【文献阅读】Hybrid model for Chinese character recognition based on Tesseract-OCR
Tesseract-OCR engine+KNN+LSTMIntroductionChinese OCR is more difficultThe number of English letters is only 26. But the number of Chinese characters that used commonly are about 2,500.the strokes of Chinese characters are complex and similar.The dif
2021-11-15 19:34:13
1654
转载 What is transfer learning?
What is transfer learning?You can take a pretrained network and use it as a starting point to learn a new task.Transfer learning only works in deep learning if the model features learned from the first task are general.
2021-11-11 20:27:27
96
原创 【文献阅读】基于深层语言模型的古汉语知识表示及自动断句研究
概述：BERT+CRF/CNN实现古文知识表示和断句2 古汉语自动断句模型条件随机场是一种经典的序列标注模型，在中文分词、词性标注、命名实体识别等自然语言处理任务中均有着广泛应用Ｚｈｅｎｇ Ｘ，ＣｈｅｎＪ，Ｓｈａｎｇ Ｇ．Ｄｅｅｐ ｎｅｕｒａｌｎｅｔｗｏｒｋ－ｂａｓｅｄＣｈｉｎｅｓｅｓｅｍａｎｔｉｃｒｏｌｅｌａｂｅｌｉｎｇ［Ｊ／ＯＬ］．ＺＴＥＣｏｍｍｕｎｉｃａｔｉｏｎｓ，２０１８：１－１２．ｈｔｔｐ：／／ｋｎｓ．ｃｎｋｉ．ｎｅｔ／ｋｃｍｓ／ｄｅｔａｉｌ／３４．１２９４．ＴＮ．２０１８０１０２．１０４５
2021-11-11 16:29:46
1541
原创 2.知识表示与知识图谱笔记
2.2.2 谓词命题（2） 个体是变元（变量）（3）个体是函数（4）个体是谓词2.2.3 谓词公式1.连接词（连词）
2021-11-07 17:16:09
3818
原创 pytorch实现BiLSTM
import torch.nn as nnclass BidirectionalLSTM(nn.Module): def __init__(self, input_size, hidden_size, output_size): super(BidirectionalLSTM, self).__init__() self.rnn = nn.LSTM(input_size, hidden_size, bidirectional=True, batch_first
2021-11-07 10:41:24
2884
1
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人