Spatio-Temporal Video Grounding (STVG) aims to localize a spatio-temporal tube that corresponds to a given language query in an untrimmed video. This is a challenging task since it involves complex vision-language understanding and spatiotemporal reasoning. Recent works have explored weakly-supervised setting in STVG to eliminate reliance on fine-grained annotations like bounding boxes or temporal stamps. However, they typically follow a simple late-fusion manner, which generates tubes independent of the text description, often resulting in failed target identification and inconsistent target tracking. To address this limitation, we propose a Tube-conditioned Reconstruction with Mutual Constraints (TubeRMC) framework that generates text-conditioned candidate tubes with pre-trained visual grounding models and further refine them via tube-conditioned reconstruction with spatio-temporal constraints. Specifically, we design three reconstruction strategies from temporal, spatial, and spatio-temporal perspectives to comprehensively capture rich tube-text correspondences. Each strategy is equipped with a Tube-conditioned Reconstructor, utilizing spatio-temporal tubes as condition to reconstruct the key clues in the query. We further introduce mutual constraints between spatial and temporal proposals to enhance their quality for reconstruction. TubeRMC outperforms existing methods on two public benchmarks VidSTG and HCSTVG. Further visualization shows that TubeRMC effectively mitigates both target identification errors and inconsistent tracking.

Human Motion Prediction (HMP) aims to predict future human poses at different moments according to observed past motion sequences. Previous approaches mainly treated the prediction of different temporal moments as a single prediction task and learned the predictions of varied moments simultaneously, which would encounter a main limitation: the learning of short-term predictions (referring to "near-future" prediction) could be hindered by the predictions of long-term (referring to "far-future" prediction) motions. In this paper, we develop a novel temporal continual learning framework called Continual Prior Compensation (CPC) to progressively train HMP models, in which we divide the prediction task of motions corresponding to varied temporal moments into several subtasks and train the model in a multi-stage manner. To mitigate the prior information forgetting in the progressive training, we further introduce a learnable random variable Prior Compensation Factor (PCF) to explicitly measure the prior knowledge loss. We theoretically show that the PCF can be efficiently learned together with the model parameters by minimizing a reasonable upper bound of the objective function. The proposed CPC is further enhanced to estimate the prior information loss for each subtask and a new framework called Continual Prior Compensation++ (CPC++) with Fine-Grained Prior Compensation Factor (FGPCF) is finally developed. Our CPC and CPC++ frameworks are quite flexible and can be easily integrated with different HMP backbone models and adapted to various datasets and applications. Extensive experiments on three HMP benchmark datasets using multiple SOTA HMP backbones (PGBIG, siMLPe, MotionMixer, and LTD) demonstrate the effectiveness and flexibility of our frameworks.

Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This is challenging as it involves deep vision-language understanding, pixel-level dense prediction and spatiotemporal reasoning. Despite notable progress in recent years, existing methods still exhibit a noticeable gap when considering all these aspects. In this work, we propose \textbf{ReferDINO}, a strong RVOS model that inherits region-level vision-language alignment from foundational visual grounding models, and is further endowed with pixel-level dense perception and cross-modal spatiotemporal reasoning. In detail, ReferDINO integrates two key components: 1) a grounding-guided deformable mask decoder that utilizes location prediction to progressively guide mask prediction through differentiable deformation mechanisms; 2) an object-consistent temporal enhancer that injects pretrained time-varying text features into inter-frame interaction to capture object-aware dynamic changes. Moreover, a confidence-aware query pruning strategy is designed to accelerate object decoding without compromising model performance. Extensive experimental results on five benchmarks demonstrate that our ReferDINO significantly outperforms previous methods (e.g., +3.9% (\mathcal{J}&\mathcal{F}) on Ref-YouTube-VOS) with real-time inference speed (51 FPS).

Video question answering (Video-QA) has emerged as a core task in the vision-language domain, which requires the models to understand a given video and answer textual questions related to the video. Compared to conventional image-language tasks, Video-QA is designed for improving the models' capacity of memorizing and integrating multi-frame temporal cues associated with the questions. While significant performance improvements have recently been witnessed on public benchmarks, in this work, we rethink whether these improvements truly stem from better understanding of video temporal context as expected. To this end, we accomplish a strong single-frame baseline model trained with knowledge distillation. With this model, we surprisingly find that visiting only one single frame, without incorporating multi-frame and temporal information, is sufficient to achieve state-of-the-art (SOTA) performance on multiple mainstream benchmarks. This finding reveals the prevalence of single-frame bias in current benchmarks for the first time. Around the single-frame bias, we conduct an in-depth analysis on multiple popular benchmarks, which demonstrate that: (i) merely relying on one frame is able to achieve comparable performance with SOTA temporal Video-QA models; (ii) simply ensembling the prediction scores of only 3 separate frames is able to surpass temporal SOTAs. Furthermore, we observe that most of the benchmarks are biased towards central segments, and even the latest benchmarks tailored for temporal reasoning still suffer from severe single-frame bias. In case study, we find two key properties of low-bias instances: the question emphasizes temporal dependency and contextual understanding, and the associated video content presents significant variability in scenes, actions or interactions. Through further analysis on compositional reasoning datasets, we find that constructing explicit object/event interactions upon videos to fill in well-designed temporal question templates can effectively reduce the single-frame bias during annotation. We hope our analysis helps facilitate future efforts in the field towards mitigating static bias and highlighting temporal reasoning.

This paper focuses on open-ended video question answering, which aims to find the correct answers from a large answer set in response to a video-related question. This is essentially a multi-label classification task, since a question may have multiple answers. However, due to annotation costs, the labels in existing benchmarks are always extremely insufficient, typically one answer per question. As a result, existing works tend to directly treat all the unlabeled answers as negative labels, leading to limited ability for generalization. In this work, we introduce a simple yet effective ranking distillation framework (RADI) to mitigate this problem without additional manual annotation. RADI employs a teacher model trained with incomplete labels to generate rankings for potential answers, which contain rich knowledge about label priority as well as label-associated visual cues, thereby enriching the insufficient labeling information. To avoid overconfidence in the imperfect teacher model, we further present two robust and parameter-free ranking distillation approaches: a pairwise approach which introduces adaptive soft margins to dynamically refine the optimization constraints on various pairwise rankings, and a listwise approach which adopts sampling-based partial listwise learning to resist the bias in teacher ranking. Extensive experiments on five popular benchmarks consistently show that both our pairwise and listwise RADIs outperform state-of-the-art methods. Further analysis demonstrates the effectiveness of our methods on the insufficient labeling problem.

We introduce a novel graph-based framework for alleviating key challenges in distantly-supervised relation extraction and demonstrate its effectiveness in the challenging and important domain of biomedical data. Specifically, we propose a graph view of sentence bags referring to an entity pair, which enables message-passing based aggregation of information related to the entity pair over the sentence bag. The proposed framework alleviates the common problem of noisy labeling in distantly supervised relation extraction and also effectively incorporates inter-dependencies between sentences within a bag. Extensive experiments on two large-scale biomedical relation datasets and the widely utilized NYT dataset demonstrate that our proposed framework significantly outperforms the state-of-the-art methods for biomedical distant supervision relation extraction while also providing excellent performance for relation extraction in the general text mining domain.

Label noise and long-tailed distributions are two major challenges in distantly supervised relation extraction. Recent studies have shown great progress on denoising, but paid little attention to the problem of long-tailed relations. In this paper, we introduce a constraint graph to model the dependencies between relation labels. On top of that, we further propose a novel constraint graph-based relation extraction framework(CGRE) to handle the two challenges simultaneously. CGRE employs graph convolution networks to propagate information from data-rich relation nodes to data-poor relation nodes, and thus boosts the representation learning of long-tailed relations. To further improve the noise immunity, a constraint-aware attention module is designed in CGRE to integrate the constraint information. Extensive experimental results indicate that CGRE achieves significant improvements over the previous methods for both denoising and long-tailed relation extraction.