This intermediate-level tutorial, titled "Gen-RecSys", merges both industrial and academic perspectives on recent advances in Generative AI for recommender systems (beyond LLMs). It aims to highlight the transformative role of generative models in modern recommender systems, which have significantly impacted the AI field-particularly with the rise of large language models (LLMs) like ChatGPT-and have contributed to a rapid convergence of the fields of search, data mining, and recommendation. By providing attendees with a modern perspective on GenAI applications in recommendation, the tutorial will emphasize how generative models can drive recommendation by unlocking and interacting with rich data representations, including behavioral, textual, and multi-modal data-knowledge highly transferable across many applications of interest to the WSDM community. Participants will learn about the categorization of generative models in recommender systems based on underlying data modalities: (i) ID-based collaborative models, (ii) text-driven models such as LLMs, and (iii) multi-modal models. Within each category, various deep generative model paradigms (e.g., AR, GAN, diffusion models) will be introduced, along with insights into their application areas. The tutorial will also cover evaluation aspects, including benchmarks, metrics, and assessments of social and ethical impacts and harms. This tutorial presents a condensed version of the industrial and academic work featured in the forthcoming book at FntIR 2024-25, titled "Recommendation with Generative Models [7]," and a shorter version prepared, and presented by the team, see GenRecSys-Survey [6].

Modern search systems offer multiple ways for expressing information needs, including image, voice, and text. Consequently, an increasing number of users seamlessly transition between these modalities to convey their intents. This emerging trend presents new opportunities for utilizing queries in different modalities to help users complete their search journeys efficiently. In this proposal, we introduce an approach to segmenting a multimodal query stream into missions, demonstrate how these in-mission queries can enhance search ranking, and outline key areas for future research.

Traditional recommender systems typically use user-item rating histories as their main data source. However, deep generative models now have the capability to model and sample from complex data distributions, including user-item interactions, text, images, and videos, enabling novel recommendation tasks. This comprehensive, multidisciplinary survey connects key advancements in RS using Generative Models (Gen-RecSys), covering: interaction-driven generative models; the use of large language models (LLM) and textual data for natural language recommendation; and the integration of multimodal models for generating and processing images/videos in RS. Our work highlights necessary paradigms for evaluating the impact and harm of Gen-RecSys and identifies open challenges. This survey accompanies a "tutorial" presented at ACM KDD'24, with supporting materials provided at: https://encr.pw/vDhLq.

Abstract Computer vision has established a foothold in the online fashion retail industry. Main product detection is a crucial step of vision-based fashion product feed parsing pipelines, focused on identifying the bounding boxes that contain the product being sold in the gallery of images of the product page. The current state-of-the-art approach does not leverage the relations between regions in the image, and treats images of the same product independently, therefore not fully exploiting visual and product contextual information. In this paper, we propose a model that incorporates Graph Convolutional Networks (GCN) that jointly represent all detected bounding boxes in the gallery as nodes. We show that the proposed method is better than the state-of-the-art, especially, when we consider the scenario where title-input is missing at inference time and for cross-dataset evaluation, our method outperforms previous approaches by a large margin.

In this paper, we introduce Shop the Look, a web-scale fashion and home product visual search system deployed at Amazon. Building such a system poses great challenges to both science and engineering practices. We leverage large-scale image data from the Amazon product catalog and adopt effective strategies to reduce the human effort required to annotate data. By employing state-of-the-art computer vision techniques, we train detection, recognition, and feature extraction models to bridge the domain gap between in-the-wild query images and product images which are taken under controlled settings. Our system is designed to achieve a balance between result accuracy and efficiency. The run-time service is optimized to provide retrieval results to users with low-latency. The scalable offline index-building pipeline adapts to the dynamic Amazon catalog that contains billions of products. We present both quantitative and qualitative evaluation results to demonstrate the performance of our system. We believe that the fast-growing Shop the Look service is shaping the way that customers shop on Amazon.

Recurrent neural networks (RNN) are popular for many computer vision tasks, including multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered for the multi-label classification task. Current approaches sort labels according to their frequency, typically ordering them in either rare-first or frequent-first. These imposed orderings do not take into account that the natural order to generate the labels can change for each image, e.g. first the dominant object before summing up the smaller objects in the image. Therefore, in this paper, we propose ways to dynamically order the ground truth labels with the predicted label sequence. This allows for the faster training of more optimal LSTM models for multi-label classification. Analysis evidences that our method does not suffer from duplicate generation, something which is common for other models. Furthermore, it outperforms other CNN-RNN models, and we show that a standard architecture of an image encoder and language decoder trained with our proposed loss obtains the state-of-the-art results on the challenging MS-COCO, WIDER Attribute and PA-100K and competitive results on NUS-WIDE.

Metric learning networks are used to compute image embeddings, which are widely used in many applications such as image retrieval and face recognition. In this paper, we propose to use network distillation to efficiently compute image embeddings with small networks. Network distillation has been successfully applied to improve image classification, but has hardly been explored for metric learning. To do so, we propose two new loss functions that model the communication of a deep teacher network to a small student network. We evaluate our system in several datasets, including CUB-200-2011, Cars-196, Stanford Online Products and show that embeddings computed using small student networks perform significantly better than those computed using standard networks of similar size. Results on a very compact network (MobileNet-0.25), which can be used on mobile devices, show that the proposed method can greatly improve Recall@1 results from 27.5\% to 44.6\%. Furthermore, we investigate various aspects of distillation for embeddings, including hint and attention layers, semi-supervised learning and cross quality distillation. (Code is available at https://github.com/yulu0724/EmbeddingDistillation).

Building upon recent Deep Neural Network architectures, current approaches lying in the intersection of Computer Vision and Natural Language Processing have achieved unprecedented breakthroughs in tasks like automatic captioning or image retrieval. Most of these learning methods, though, rely on large training sets of images associated with human annotations that specifically describe the visual content. In this paper we propose to go a step further and explore the more complex cases where textual descriptions are loosely related to the images. We focus on the particular domain of news articles in which the textual content often expresses connotative and ambiguous relations that are only suggested but not directly inferred from images. We introduce an adaptive CNN architecture that shares most of the structure for multiple tasks including source detection, article illustration and geolocation of articles. Deep Canonical Correlation Analysis is deployed for article illustration, and a new loss function based on Great Circle Distance is proposed for geolocation. Furthermore, we present BreakingNews, a novel dataset with approximately 100K news articles including images, text and captions, and enriched with heterogeneous meta-data (such as GPS coordinates and user comments). We show this dataset to be appropriate to explore all aforementioned problems, for which we provide a baseline performance using various Deep Learning architectures, and different representations of the textual and visual features. We report very promising results and bring to light several limitations of current state-of-the-art in this kind of domain, which we hope will help spur progress in the field.

The intersection of Computer Vision and Natural Language Processing has been a hot topic of research in recent years, with results that were unthinkable only a few years ago. In view of this progress, we want to highlight online news articles as a potential next step for this area of research. The rich interrelations of text, tags, images or videos, as well as a vast corpus of general knowledge are an exciting benchmark for high-capacity models such as the deep neural networks. In this paper we present a series of tasks and baseline approaches to leverage corpus such as the BreakingNews dataset.

Ariadna Quattoni, Arnau Ramisa, Pranava Swaroop Madhyastha, Edgar Simo-Serra, Francesc Moreno-Noguer. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

We investigate the role that geometric, textual and visual features play in the task of predicting a preposition that links two visual entities depicted in an image.The task is an important part of the subsequent process of generating image descriptions.We explore the prediction of prepositions for a pair of entities, both in the case when the labels of such entities are known and unknown.In all situations we found clear evidence that all three features contribute to the prediction task.

We propose a robust and efficient method to estimate the pose of a camera with respect to complex 3D textured models of the environment that can potentially contain more than 100; 000 points. To tackle this problem we follow a top down approach where we combine high-level deep network classifiers with low level geometric approaches to come up with a solution that is fast, robust and accurate. Given an input image, we initially use a pre-trained deep network to compute a rough estimation of the camera pose. This initial estimate constrains the number of 3D model points that can be seen from the camera viewpoint. We then establish 3D-to-2D correspondences between these potentially visible points of the model and the 2D detected image features. Accurate pose estimation is finally obtained from the 2D-to-3D correspondences using a novel PnP algorithm that rejects outliers without the need to use a RANSAC strategy, and which is between 10 and 100 times faster than other methods that use it. Two real experiments dealing with very large and complex 3D models demonstrate the effectiveness of the approach.

Most current depth sensors provide 2.5D range images in which depth values are assigned to a rectangular 2D array. In this paper we take advantage of this structured information to build an efficient shape descriptor which is about two orders of magnitude faster than competing approaches, while showing similar performance in several tasks involving deformable object recognition. Given a 2D patch surrounding a point and its associated depth values, we build the descriptor for that point, based on the cumulative distances between their normals and a discrete set of normal directions. This processing is made very efficient using integral images, even allowing to compute descriptors for every range image pixel in a few seconds. The discriminative power of our descriptor, dubbed FINDDD, is evaluated in three different scenarios: recognition of specific cloth wrinkles, instance recognition from geometry alone, and detection of reliable and informed grasping points.

Markerless 3D human pose detection from a single image is a severely underconstrained problem because different 3D poses can have similar image projections. In order to handle this ambiguity, current approaches rely on prior shape models that can only be correctly adjusted if 2D image features are accurately detected. Unfortunately, although current 2D part detector algorithms have shown promising results, they are not yet accurate enough to guarantee a complete disambiguation of the 3D inferred shape. In this paper, we introduce a novel approach for estimating 3D human pose even when observations are noisy. We propose a stochastic sampling strategy to propagate the noise from the image plane to the shape space. This provides a set of ambiguous 3D shapes, which are virtually undistinguishable from their image projections. Disambiguation is then achieved by imposing kinematic constraints that guarantee the resulting pose resembles a 3D human shape. We validate the method on a variety of situations in which state-of-the-art 2D detectors yield either inaccurate estimations or partly miss some of the body parts.

Detecting grasping points is a key problem in cloth manipulation. Most current approaches follow a multiple re-grasp strategy for this purpose, in which clothes are sequentially grasped from different points until one of them yields to a desired configuration. In this paper, by contrast, we circumvent the need for multiple re-graspings by building a robust detector that identifies the grasping points, generally in one single step, even when clothes are highly wrinkled. In order to handle the large variability a deformed cloth may have, we build a Bag of Features based detector that combines appearance and 3D geometry features. An image is scanned using a sliding window with a linear classifier, and the candidate windows are refined using a non-linear SVM and a “grasp goodness” criterion to select the best grasping point. We demonstrate our approach detecting collars in deformed polo shirts, using a Kinect camera. Experimental results show a good performance of the proposed method not only in identifying the same trained textile object part under severe deformations and occlusions, but also the corresponding part in other clothes, exhibiting a degree of generalization.

Attributes were recently shown to give excellent results for category recognition. In this paper, we demonstrate their performance in the context of image retrieval. First, we show that retrieving images of particular objects based on attribute vectors gives results comparable to the state of the art. Second, we demonstrate that combining attribute and Fisher vectors improves performance for retrieval of particular objects as well as categories. Third, we implement an efficient coding technique for compressing the combined descriptor to very small codes. Experimental results on the Holidays dataset show that our approach significantly outperforms the state of the art, even for a very compact representation of 16 bytes per image. Retrieving category images is evaluated on the “web-queries” dataset. We show that attribute features combined with Fisher vectors improve the performance and that combined image features can supplement text features.

We propose an efficient method, built on the popular Bag of Features approach, that obtains robust multiclass pixel-level object segmentation of an image in less than 500ms, with results comparable or better than most state of the art methods. We introduce the Integral Linear Classifier (ILC), that can readily obtain the classification score for any image sub-window with only 6 additions and 1 product by fusing the accumulation and classification steps in a single operation. In order to design a method as efficient as possible, our building blocks are carefully selected from the quickest in the state of the art. More precisely, we evaluate the performance of three popular local descriptors, that can be very efficiently computed using integral images, and two fast quantization methods: the Hierarchical K-Means, and the Extremely Randomized Forest. Finally, we explore the utility of adding spatial bins to the Bag of Features histograms and that of cascade classifiers to improve the obtained segmentation. Our method is compared to the state of the art in the difficult Graz-02 and PASCAL 2007 Segmentation Challenge datasets.

Selecting which algorithms should be used by a mobile robot computer vision system is a decision that is usually made a priori by the system developer, based on past experience and intuition, not systematically taking into account information that can be found in the images and in the visual process itself to learn which algorithm should be used, in execution time. This paper presents a method that uses Reinforcement Learning to decide which algorithm should be used to recognize objects seen by a mobile robot in an indoor environment, based on simple attributes extracted on-line from the images, such as mean intensity and intensity deviation. Two state-of-the-art object recognition algorithms can be selected: the constellation method proposed by Lowe together with its interest point detector and descriptor, the Scale-Invariant Feature Transform and a bag of features approach. A set of empirical evaluations was conducted using a household mobile robots image database, and results obtained shows that the approach adopted here is very promising.

This paper presents a vision-based approach for mobile robot localization. The environmental model is topological. The new approach uses a constellation of different types of affine covariant regions to characterize a place. This type of representation permits a reliable and distinctive environment modeling. The performance of the proposed approach is evaluated using a database of panoramic images from different rooms. Additionally, we compare different combinations of complementary feature region detectors to find the one that achieves the best results. Our experimental results show promising results for this new localization method. Additionally, similarly to what happens with single detectors, different combinations exhibit different strengths and weaknesses depending on the situation, suggesting that a context-aware method to combine the different detectors would improve the localization results.