We propose the first mechanism to train object detection models from weak supervision in the form of captions at the image level. Language-based supervision for detection is appealing and inexpensive: many blogs with images and descriptive text written by human users exist. However, there is significant noise in this supervision: captions do not mention all objects that are shown, and may mention extraneous concepts. We first propose a technique to determine which image-caption pairs provide suitable signal for supervision. We further propose several complementary mechanisms to extract image-level pseudo labels for training from the caption. Finally, we train an iterative weakly-supervised object detection model from these image-level pseudo labels. We use captions from four datasets (COCO, Flickr30K, MIRFlickr1M, and Conceptual Captions) whose level of noise varies. We evaluate our approach on two object detection datasets. Weighting the labels extracted from different captions provides a boost over treating all captions equally. Further, our primary proposed technique for inferring pseudo labels for training at the image level, outperforms alternative techniques under a wide variety of settings. Both techniques generalize to datasets beyond the one they were trained on.

Learning to localize and name object instances is a fundamental problem in vision, but state-of-the-art approaches rely on expensive bounding box supervision. While weakly supervised detection (WSOD) methods relax the need for boxes to that of image-level annotations, even cheaper supervision is naturally available in the form of unstructured textual descriptions that users may freely provide when uploading image content. However, straightforward approaches to using such data for WSOD wastefully discard captions that do not exactly match object names. Instead, we show how to squeeze the most information out of these captions by training a text-only classifier that generalizes beyond dataset boundaries. Our discovery provides an opportunity for learning detection models from noisy but more abundant and freely-available caption data. We also validate our model on three classic object detection benchmarks and achieve state-of-the-art WSOD performance. Our code is available at https://github.com/yekeren/Cap2Det.

Spatiotemporal feature learning in videos is a fundamental problem in computer vision. This paper presents a new architecture, termed as Appearance-and-Relation Network (ARTNet), to learn video representation in an end-to-end manner. ARTNets are constructed by stacking multiple generic building blocks, called as SMART, whose goal is to simultaneously model appearance and relation from RGB input in a separate and explicit manner. Specifically, SMART blocks decouple the spatiotemporal learning module into an appearance branch for spatial modeling and a relation branch for temporal modeling. The appearance branch is implemented based on the linear combination of pixels or filter responses in each frame, while the relation branch is designed based on the multiplicative interactions between pixels or filter responses across multiple frames. We perform experiments on three action recognition benchmarks: Kinetics, UCF101, and HMDB51, demonstrating that SMART blocks obtain an evident improvement over 3D convolutions for spatiotemporal feature learning. Under the same training setting, ARTNets achieve superior performance on these three datasets to the existing state-of-the-art methods.1

Person re-identification is to match pedestrian images from disjoint camera views detected by pedestrian detectors. Challenges are presented in the form of complex variations of lightings, poses, viewpoints, blurring effects, image resolutions, camera settings, occlusions and background clutter across camera views. In addition, misalignment introduced by the pedestrian detector will affect most existing person re-identification methods that use manually cropped pedestrian images and assume perfect detection. In this paper, we propose a novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter. All the key components are jointly optimized to maximize the strength of each component when cooperating with others. In contrast to existing works that use handcrafted features, our method automatically learns features optimal for the re-identification task from data. The learned filter pairs encode photometric transforms. Its deep architecture makes it possible to model a mixture of complex photometric and geometric transforms. We build the largest benchmark re-id dataset with 13, 164 images of 1, 360 pedestrians. Unlike existing datasets, which only provide manually cropped pedestrian images, our dataset provides automatically detected bounding boxes for evaluation close to practical applications. Our neural network significantly outperforms state-of-the-art methods on this dataset.

The performance of a generic pedestrian detector may drop significantly when it is applied to a specific scene due to the mismatch between the source training set and samples from the target scene. We propose a new approach of automatically transferring a generic pedestrian detector to a scene-specific detector in static video surveillance without manually labeling samples from the target scene. The proposed transfer learning framework consists of four steps. 1) Through exploring the indegrees from target samples to source samples on a visual affinity graph, the source samples are weighted to match the distribution of target samples. 2) It explores a set of context cues to automatically select samples from the target scene, predicts their labels, and computes confidence scores to guide transfer learning. 3) The confidence scores propagate among target samples according to their underlying visual structures. 4) Target samples with higher confidence scores have larger influence on training scene-specific detectors. All these considerations are formulated under a single objective function called confidence-encoded SVM, which avoids hard thresholding on confidence scores. During test, only the appearance-based detector is used without context cues. The effectiveness is demonstrated through experiments on two video surveillance data sets. Compared with a generic detector, it improves the detection rates by 48 and 36 percent at one false positive per image (FPPI) on the two data sets, respectively. The training process converges after one or two iterations on the data sets in experiments.

In this paper, we propose a new approach for matching images observed in different camera views with complex cross-view transforms and apply it to person re-identification. It jointly partitions the image spaces of two camera views into different configurations according to the similarity of cross-view transforms. The visual features of an image pair from different views are first locally aligned by being projected to a common feature space and then matched with softly assigned metrics which are locally optimized. The features optimal for recognizing identities are different from those for clustering cross-view transforms. They are jointly learned by utilizing sparsity-inducing norm and information theoretical regularization. This approach can be generalized to the settings where test images are from new camera views, not the same as those in the training set. Extensive experiments are conducted on public datasets and our own dataset. Comparisons with the state-of-the-art metric learning and person re-identification methods show the superior performance of our approach.

The performance of a generic pedestrian detector may drop significantly when it is applied to a specific scene due to mismatch between the source dataset used to train the detector and samples in the target scene. In this paper, we investigate how to automatically train a scene-specific pedestrian detector starting with a generic detector in video surveillance without further manually labeling any samples under a novel transfer learning framework. It tackles the problem from three aspects. (1) With a graphical representation and through exploring the indegrees from target samples to source samples, the source samples are properly re-weighted. The indegrees detect the boundary between the distributions of the source dataset and the target dataset. The re-weighted source dataset better matches the target scene. (2) It takes the context information from motions, scene structures and scene geometry as the confidence scores of samples from the target scene to guide transfer learning. (3) The confidence scores propagate among samples on a graph according to the underlying visual structures of samples. All these considerations are formulated under a single objective function called Confidence-Encoded SVM. At the test stage, only the appearance-based detector is used without the context cues. The effectiveness of the proposed framework is demonstrated through experiments on two video surveillance datasets. Compared with a generic pedestrian detector, it significantly improves the detection rate by 48% and 36% at one false positive per image on the two datasets respectively.

In this paper, we consider a novel problem referred to as term filtering with bounded error to reduce the term (feature) space by eliminating terms without (or with bounded) information loss. Different from existing works, the obtained term space provides a complete view of the original term space. More interestingly, several important questions can be answered such as: 1) how different terms interact with each other and 2) how the filtered terms can be represented by the other terms. We perform a theoretical investigation of the term filtering problem and link it to the Geometric Covering By Discs problem, and prove its NP-hardness. We present two novel approaches for both lossless and lossy term filtering with bounds on the introduced error. Experimental results on multiple text mining tasks validate the effectiveness of the proposed approaches.