Recent advances in diffusion-based text-to-image models have simplified creating high-fidelity images, but preserving the identity (ID) of specific elements, like a personal dog, is still challenging. Object customization, using reference images and textual descriptions, is key to addressing this issue. Current object customization methods are either object-specific, requiring extensive fine-tuning, or object-agnostic, offering zero-shot customization but limited to specialized domains. The primary issue of promoting zero-shot object customization from specific domains to the general domain is to establish a large-scale general ID dataset for model pre-training, which is time-consuming and labor-intensive. In this paper, we propose a novel pipeline to construct a large dataset of general objects and build the Multi-Category ID-Consistent (MC-IDC) dataset, featuring 315k text-image samples across 10k categories. With the help of MC-IDC, we introduce Customizing Anything (CustAny), a zero-shot framework that maintains ID fidelity and supports flexible text editing for general objects. CustAny features three key components: a general ID extraction module, a dual-level ID injection module, and an ID-aware decoupling module, allowing it to customize any object from a single reference image and text prompt. Experiments demonstrate that CustAny outperforms existing methods in both general object customization and specialized domains like human customization and virtual try-on. Our contributions include a large-scale dataset, the CustAny framework and novel ID processing to advance this field. The official project page is in https://lingjiekong-fdu.github.io.

Multi-object tracking (MOT) is a technique that aims to detect multiple objects in a single frame and maintain their identities in a given video sequence. Currently, the tracking-by-detection paradigm stands out as the most effective approach for MOT, encompassing object detection, person re-identification (Re-ID), and data association. In this paper, we propose enhancements to the Re-ID and data association modules, emphasizing the pivotal role of appearance information in achieving robust tracking quality. To capture more discriminative features, we introduce a network based on partial-level features. We also employ reparameterization to remove residual connection blocks from the backbone network without altering the original output to enhance tracking accuracy while optimizing computational efficiency. Moreover, the utilization of bounding boxes significantly influences tracking performance. We introduce an adaptive threshold mechanism and incorporate gating functions for data association, ensuring efficient use of each bounding box while minimizing trajectory fragmentation and missed detections. Experimental results illustrate that our proposed method attains high detection and tracking accuracy, particularly excelling in challenging video sequences. Our approach demonstrates comparable performance to state-of-the-art trackers on various benchmarks, including MOT17 and MOT20, where MOT20 presents frequent and severe interactions and occlusions.

This paper addresses the multiorder open-dimension three-dimensional rectangular packing problem (3D-MOSB-ODRPP), which involves packing rectangular items from multiple orders into a single, size-adjustable container. We propose a novel metaheuristic approach combining a genetic algorithm with the Gurobi solver. The algorithm incorporates a lower neighborhood search strategy and is underpinned by a mathematical model representing the multiorder open-dimension packing scenario. Extensive experiments validate the effectiveness of the proposed approach. The LNSGA algorithm outperforms Gurobi and the traditional genetic algorithm in solution quality and computational efficiency. For small-scale instances, LNSGA achieves optimal values in most cases. LNSGA demonstrates significant optimization improvements over Gurobi and the genetic algorithm for large-scale instances. The superior performance is attributed to the effective integration of the lower neighborhood search mechanism and the Gurobi solver. This study offers valuable insights for optimizing the packing process in e-commerce warehousing and logistics operations.

Previous efforts in vision community are mostly made on learning good representations from visual patterns. Beyond this, this paper emphasizes the high-level ability of causal reasoning. We thus present a case study of solving the challenging task of Overall Survival (OS) time in primary liver cancers. Critically, the prediction of OS time at the early stage remains challenging, due to the unobvious image patterns of reflecting the OS. To this end, we propose a causal inference system by leveraging the intraoperative attributes and the correlation among them, as an intermediate supervision to bridge the gap between the images and the final OS. Particularly, we build a causal graph, and train the images to estimate the intraoperative attributes for final as prediction. We present a novel Causally-aware Intraoperative Imputation Model (CAWIM) that can sequentially predict each attribute using its parent nodes in the estimated causal graph. To determine the causal directions, we propose a splitting-voting mechanism, which votes for the direction for each pair of adjacent nodes among multiple predictions obtained via causal discovery from heterogeneity. The practicability and effectiveness of our method are demonstrated by the promising results on liver cancer dataset of 361 patients with long-term observations.

To maximize signal collection in nonlinear optical microscopy, non-descanned epi-detection is generally adopted for in vivo imaging. However, because of severe scattering in biological samples, most of the emitted fluorescence photons go beyond the collection angles of objectives and thus cannot be detected. Here, we propose an extended detection scheme to enhance the collection of scattered photons in nonlinear fluorescence microscopy using a silicon photomultiplier array ahead of the front apertures of objectives. We perform numerical simulations to demonstrate the enhanced fluorescence collection via extended epi-detection in the multi-photon fluorescence imaging of human skin and mouse brain through craniotomy windows and intact skulls. For example, with red fluorescence emission at a depth of 600 µm in human skin, the increased collection can be as much as about 150% with a 10×, 0.6-NA objective. We show that extended epi-detection is a generally applicable, feasible technique for use in nonlinear fluorescence microscopy to enhance signal detection.