Related papers: SID-Coord: Coordinating Semantic IDs for ID-based …
Recent advancements in adapting vision-language pre-training models like CLIP for person re-identification (ReID) tasks often rely on complex adapter design or modality-specific tuning while neglecting cross-modal interaction, leading to…
Composed Video Retrieval (CVR) is a challenging video retrieval task that utilizes multi-modal queries, consisting of a reference video and modification text, to retrieve the desired target video. The core of this task lies in understanding…
Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview. Most current pretraining methods, however, are limited to one or two modalities. We present i-Code, a self-supervised…
Person re-identification (reID) aims to match person images to retrieve the ones with the same identity. This is a challenging task, as the images to be matched are generally semantically misaligned due to the diversity of human poses and…
Object re-identification (ReID) in large camera networks faces numerous challenges. First, the similar appearances of objects degrade ReID performance, a challenge that needs to be addressed by existing appearance-based ReID methods.…
Semantic identifiers (IDs) have proven effective in adapting large language models for generative recommendation and retrieval. However, existing methods often suffer from semantic ID conflicts, where semantically similar documents (or…
We present a novel scalable framework for image change detection (ICD) from an on-board 3D imagery system. We argue that existing ICD systems are constrained by the time required to align a given query image with individual reference image…
Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources…
With the rise of modern search and recommendation platforms, insufficient collaborative information of cold-start items exacerbates the Matthew effect of existing platform items, challenging platform diversity and becoming a longstanding…
Semantic ID-based generative recommendation represents items as sequences of discrete tokens, but it inherently faces a trade-off between representational expressiveness and computational efficiency. Residual Quantization (RQ)-based…
Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches mainly focus on horizontal objects, leaving multi-oriented…
Generative recommender systems have recently attracted attention by formulating next-item prediction as an autoregressive sequence generation task. However, most existing methods optimize standard next-token likelihood and implicitly treat…
In incremental learning, enhancing the generality of knowledge is crucial for adapting to dynamic data inputs. It can develop generalized representations or more balanced decision boundaries, preventing the degradation of long-term…
Generative Retrieval (GR) is rapidly transforming e-commerce search by replacing traditional multi-stage pipelines with the autoregressive decoding of structured Semantic IDs (SIDs). Despite this architectural efficiency, aligning GR models…
Modern Sequential Recommendation (SR) models commonly utilize modality features to represent items, motivated in large part by recent advancements in language and vision modeling. To do so, several works completely replace ID embeddings…
Industrial recommender systems increasingly leverage lifelong user behavior histories and rich multi-modal content to capture evolving user preferences. However, effectively integrating multi-modal features into lifelong interest modeling…
Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised…
Most referring object detection (ROD) models, especially the modern grounding detectors, are designed for data-rich conditions, yet many practical deployments, such as robotics, augmented reality, and other specialized domains, would face…
Integrating product catalogs and user behavior into LLMs can enhance recommendations with broad world knowledge, but the scale of real-world item catalogs, often containing millions of discrete item identifiers (Item IDs), poses a…
Structured representation of product information is a major bottleneck for the efficiency of e-commerce platforms, especially in second-hand ecommerce platforms. Currently, most product information are organized based on manually curated…