When re-finding items, users who forget or are uncertain about identifying details often rely on creative strategies for expressing their information needs -- complex queries that describe content elements (e.g., book characters or events), information beyond the document text (e.g., descriptions of book covers), or personal context (e.g., when they read a book). This retrieval setting, called tip of the tongue (TOT), is especially challenging for models heavily reliant on lexical and semantic overlap between query and document text. In this work, we introduce a simple yet effective framework for handling such complex queries by decomposing the query into individual clues, routing those as sub-queries to specialized retrievers, and ensembling the results. This approach allows us to take advantage of off-the-shelf retrievers (e.g., CLIP for retrieving images of book covers) or incorporate retriever-specific logic (e.g., date constraints). We show that our framework incorportating query decompositions into retrievers can improve gold book recall up to 7% relative again for Recall@5 on a new collection of 14,441 real-world query-book pairs from an online community for resolving TOT inquiries.
We present a unified framework for camera-space 3D hand pose estimation from a single RGB image based on 3D implicit representation. As opposed to recent works, most of which first adopt holistic or pixel-level dense regression to obtain relative 3D hand pose and then follow with complex second-stage operations for 3D global root or scale recovery, we propose a novel unified 3D dense regression scheme to estimate camera-space 3D hand pose via dense 3D point-wise voting in camera frustum. Through direct dense modeling in 3D domain inspired by Pixel-aligned Implicit Functions for 3D detailed reconstruction, our proposed Neural Voting Field (NVF) fully models 3D dense local evidence and hand global geometry, helping to alleviate common 2D-to-3D ambiguities. Specifically, for a 3D query point in camera frustum and its pixel-aligned image feature, NVF, represented by a Multi-Layer Perceptron, regresses: (i) its signed distance to the hand surface; (ii) a set of 4D offset vectors (1D voting weight and 3D directional vector to each hand joint). Following a vote-casting scheme, 4D offset vectors from near-surface points are selected to calculate the 3D hand joint coordinates by a weighted average. Experiments demonstrate that NVF outperforms existing state-of-the-art algorithms on FreiHAND dataset for camera-space 3D hand pose estimation. We also adapt NVF to the classic task of root-relative 3D hand pose estimation, for which NVF also obtains state-of-the-art results on HO3D dataset.
Model merging (e.g., via interpolation or task arithmetic) fuses multiple models trained on different tasks to generate a multi-task solution. The technique has been proven successful in previous studies, where the models are trained on similar tasks and with the same initialization. In this paper, we expand on this concept to a multimodal setup by merging transformers trained on different modalities. Furthermore, we conduct our study for a novel goal where we can merge vision, language, and cross-modal transformers of a modality-specific architecture to create a parameter-efficient modality-agnostic architecture. Through comprehensive experiments, we systematically investigate the key factors impacting model performance after merging, including initialization, merging mechanisms, and model architectures. Our analysis leads to an effective training recipe for matching the performance of the modality-agnostic baseline (i.e. pre-trained from scratch) via model merging. Our code is available at: https://github.com/ylsung/vl-merging
The most recent efforts in video matting have focused on eliminating trimap dependency since trimap annotations are expensive and trimap-based methods are less adaptable for real-time applications. Despite the latest tripmap-free methods showing promising results, their performance often degrades when dealing with highly diverse and unstructured videos. We address this limitation by introducing Adaptive Matting for Dynamic Videos, termed AdaM, which is a framework designed for simultaneously differentiating foregrounds from backgrounds and capturing alpha matte details of human subjects in the foreground. Two interconnected network designs are employed to achieve this goal: (1) an encoder-decoder network that produces alpha mattes and intermediate masks which are used to guide the transformer in adaptively decoding foregrounds and backgrounds, and (2) a transformer network in which long- and short-term attention combine to retain spatial and temporal contexts, facilitating the decoding of foreground details. We benchmark and study our methods on recently introduced datasets, showing that our model notably improves matting realism and temporal coherence in complex real-world videos and achieves new best-in-class generalizability. Further details and examples are available at https://github.com/microsoft/AdaM.
We propose Filtering Inversion (FINV), a learning framework and optimization process that predicts a renderable 3D object representation from one or few partial views. FINV addresses the challenge of synthesizing novel views of objects from partial observations, spanning cases where the object is not entirely in view, is partially occluded, or is only observed from similar views. To achieve this, FINV learns shape priors by training a 3D generative model. At inference, given one or more views of a novel real-world object, FINV first finds a set of latent codes for the object by inverting the generative model from multiple initial seeds. Maintaining the set of latent codes, FINV filters and resamples them after receiving each new observation, akin to particle filtering. The generator is then finetuned for each latent code on the available views in order to adapt to novel objects. We show that FINV successfully synthesizes novel views of real-world objects (e.g., chairs, tables, and cars), even if the generative prior is trained only on synthetic objects. The ability to address the sim-to-real problem allows FINV to be used for object categories without real-world datasets. FINV achieves state-of-the-art performance on multiple real-world datasets, recovers object shape and texture from partial and sparse views, is robust to occlusion, and is able to incrementally improve its representation with more observations.
This study explores the concept of equivariance in vision-language foundation models (VLMs), focusing specifically on the multimodal similarity function that is not only the major training objective but also the core delivery to support downstream tasks. Unlike the existing image-text similarity objective which only categorizes matched pairs as similar and unmatched pairs as dissimilar, equivariance also requires similarity to vary faithfully according to the semantic changes. This allows VLMs to generalize better to nuanced and unseen multimodal compositions. However, modeling equivariance is challenging as the ground truth of semantic change is difficult to collect. For example, given an image-text pair about a dog, it is unclear to what extent the similarity changes when the pixel is changed from dog to cat? To this end, we propose EqSim, a regularization loss that can be efficiently calculated from any two matched training pairs and easily pluggable into existing image-text retrieval fine-tuning. Meanwhile, to further diagnose the equivariance of VLMs, we present a new challenging benchmark EqBen. Compared to the existing evaluation sets, EqBen is the first to focus on "visual-minimal change". Extensive experiments show the lack of equivariance in current VLMs and validate the effectiveness of EqSim. Code is available at \url{https://github.com/Wangt-CN/EqBen}.
We propose Text2Motion, a language-based planning framework enabling robots to solve sequential manipulation tasks that require long-horizon reasoning. Given a natural language instruction, our framework constructs both a task- and policy-level plan that is verified to reach inferred symbolic goals. Text2Motion uses skill feasibility heuristics encoded in learned Q-functions to guide task planning with Large Language Models. Whereas previous language-based planners only consider the feasibility of individual skills, Text2Motion actively resolves geometric dependencies spanning skill sequences by performing policy sequence optimization during its search. We evaluate our method on a suite of problems that require long-horizon reasoning, interpretation of abstract goals, and handling of partial affordance perception. Our experiments show that Text2Motion can solve these challenging problems with a success rate of 64%, while prior state-of-the-art language-based planning methods only achieve 13%. Text2Motion thus provides promising generalization characteristics to semantically diverse sequential manipulation tasks with geometric dependencies between skills.
We propose MM-REACT, a system paradigm that integrates ChatGPT with a pool of vision experts to achieve multimodal reasoning and action. In this paper, we define and explore a comprehensive list of advanced vision tasks that are intriguing to solve, but may exceed the capabilities of existing vision and vision-language models. To achieve such advanced visual intelligence, MM-REACT introduces a textual prompt design that can represent text descriptions, textualized spatial coordinates, and aligned file names for dense visual signals such as images and videos. MM-REACT's prompt design allows language models to accept, associate, and process multimodal information, thereby facilitating the synergetic combination of ChatGPT and various vision experts. Zero-shot experiments demonstrate MM-REACT's effectiveness in addressing the specified capabilities of interests and its wide application in different scenarios that require advanced visual understanding. Furthermore, we discuss and compare MM-REACT's system paradigm with an alternative approach that extends language models for multimodal scenarios through joint finetuning. Code, demo, video, and visualization are available at https://multimodal-react.github.io/
We present Mesh Pre-Training (MPT), a new pre-training framework that leverages 3D mesh data such as MoCap data for human pose and mesh reconstruction from a single image. Existing work in 3D pose and mesh reconstruction typically requires image-mesh pairs as the training data, but the acquisition of 2D-to-3D annotations is difficult. In this paper, we explore how to leverage 3D mesh data such as MoCap data, that does not have RGB images, for pre-training. The key idea is that even though 3D mesh data cannot be used for end-to-end training due to a lack of the corresponding RGB images, it can be used to pre-train the mesh regression transformer subnetwork. We observe that such pre-training not only improves the accuracy of mesh reconstruction from a single image, but also enables zero-shot capability. We conduct mesh pre-training using 2 million meshes. Experimental results show that MPT advances the state-of-the-art results on Human3.6M and 3DPW datasets. We also show that MPT enables transformer models to have zero-shot capability of human mesh reconstruction from real images. In addition, we demonstrate the generalizability of MPT to 3D hand reconstruction, achieving state-of-the-art results on FreiHAND dataset.
Recently, large-scale text-to-image (T2I) models have shown impressive performance in generating high-fidelity images, but with limited controllability, e.g., precisely specifying the content in a specific region with a free-form text description. In this paper, we propose an effective technique for such regional control in T2I generation. We augment T2I models' inputs with an extra set of position tokens, which represent the quantized spatial coordinates. Each region is specified by four position tokens to represent the top-left and bottom-right corners, followed by an open-ended natural language regional description. Then, we fine-tune a pre-trained T2I model with such new input interface. Our model, dubbed as ReCo (Region-Controlled T2I), enables the region control for arbitrary objects described by open-ended regional texts rather than by object labels from a constrained category set. Empirically, ReCo achieves better image quality than the T2I model strengthened by positional words (FID: 8.82->7.36, SceneFID: 15.54->6.51 on COCO), together with objects being more accurately placed, amounting to a 20.40% region classification accuracy improvement on COCO. Furthermore, we demonstrate that ReCo can better control the object count, spatial relationship, and region attributes such as color/size, with the free-form regional description. Human evaluation on PaintSkill shows that ReCo is +19.28% and +17.21% more accurate in generating images with correct object count and spatial relationship than the T2I model.