# Multiple Object Recognition with Visual Attention Source: [Multiple Object Recognition with Visual Attention]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:06:28.249Z Authors: Jimmy Ba, Volodymyr Mnih, Koray Kavukcuoglu Published: 2014-12-24T20:58:23.000Z ## Abstract We present an attention-based model for recognizing multiple objects in images. The proposed model is a deep recurrent neural network trained with reinforcement learning to attend to the most relevant regions of the input image. We show that the model learns to both localize and recognize multiple objects despite being given only class labels during training. We evaluate the model on the challenging task of transcribing house number sequences from Google Street View images and show that it is both more accurate than the state-of-the-art convolutional networks and uses fewer parameters and less computation. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Visual Search on COCO-Search18 cross-task](): Visual Search; COCO-Search18 cross-task; Accuracy (%): 14.34. - [Scanpath Alignment on CIFAR-10](): Scanpath Alignment; CIFAR-10; DTW: 837.14. - [Image Classification on ImageNet (Accuracy and Input Resolution)](): Image Classification; ImageNet; Top-1 Accuracy: 67.5. - [Classification on COCO](): Classification; COCO; Accuracy: 43.32. - [Image Classification on ImageNet100 (test)](): Image Classification; ImageNet100 (test); Top-1 Acc: 21.44. - [Image Classification on CIFAR-10 (Accuracy)](): Image Classification; CIFAR-10; Accuracy: 64.81. ## Original sources and implementation [Original paper]() [PDF]()