{ "metadata": { "model_name": "QQMM-embed-v2", "model_backbone": "QQMM", "model_size": 8.29, "embedding_dimension": 3584, "max_length_tokens": 4096, "model_release_date": "2025-09-15", "data_source": "Self-Reported", "url": "https://github.com/QQ-MM/QQMM-embed", "report_generated_date": "2025-09-15T17:33:58.137833" }, "metrics": { "image": { "ImageNet-1K": { "hit@1": 0.835, "hit@5": 0.974, "hit@10": 0.986, "ndcg_linear@1": 0.835, "ndcg_linear@5": 0.9134553571967777, "ndcg_linear@10": 0.9173520687222101, "ndcg_exponential@1": 0.835, "ndcg_exponential@5": 0.9134553571967777, "ndcg_exponential@10": 0.9173520687222101, "precision@1": 0.835, "precision@5": 0.19480000000000003, "precision@10": 0.09860000000000002, "recall@1": 0.835, "recall@5": 0.974, "recall@10": 0.986, "f1@1": 0.835, "f1@5": 0.3246666666666666, "f1@10": 0.17927272727272725, "map@1": 0.835, "map@5": 0.8928833333333333, "map@10": 0.8945011904761905, "mrr@1": 0.835, "mrr@5": 0.8928833333333333, "mrr@10": 0.8945011904761905, "num_pred": 1000, "num_data": 1000 }, "N24News": { "hit@1": 0.824, "hit@5": 0.962, "hit@10": 0.992, "ndcg_linear@1": 0.824, "ndcg_linear@5": 0.9008865745786582, "ndcg_linear@10": 0.9108658673721785, "ndcg_exponential@1": 0.824, "ndcg_exponential@5": 0.9008865745786582, "ndcg_exponential@10": 0.9108658673721785, "precision@1": 0.824, "precision@5": 0.19240000000000004, "precision@10": 0.09920000000000001, "recall@1": 0.824, "recall@5": 0.962, "recall@10": 0.992, "f1@1": 0.824, "f1@5": 0.3206666666666667, "f1@10": 0.18036363636363636, "map@1": 0.824, "map@5": 0.8802666666666666, "map@10": 0.8845468253968254, "mrr@1": 0.824, "mrr@5": 0.8802666666666666, "mrr@10": 0.8845468253968254, "num_pred": 1000, "num_data": 1000 }, "HatefulMemes": { "hit@1": 0.796, "hit@5": 1.0, "hit@10": 1.0, "ndcg_linear@1": 0.796, "ndcg_linear@5": 0.9247096697285774, "ndcg_linear@10": 0.9247096697285774, "ndcg_exponential@1": 0.796, "ndcg_exponential@5": 0.9247096697285774, "ndcg_exponential@10": 0.9247096697285774, "precision@1": 0.796, "precision@5": 0.20000000000000004, "precision@10": 0.10000000000000002, "recall@1": 0.796, "recall@5": 1.0, "recall@10": 1.0, "f1@1": 0.796, "f1@5": 0.3333333333333333, "f1@10": 0.18181818181818182, "map@1": 0.796, "map@5": 0.898, "map@10": 0.898, "mrr@1": 0.796, "mrr@5": 0.898, "mrr@10": 0.898, "num_pred": 1000, "num_data": 1000 }, "VOC2007": { "hit@1": 0.928, "hit@5": 0.988, "hit@10": 0.998, "ndcg_linear@1": 0.928, "ndcg_linear@5": 0.963195714692262, "ndcg_linear@10": 0.9665932455002518, "ndcg_exponential@1": 0.928, "ndcg_exponential@5": 0.963195714692262, "ndcg_exponential@10": 0.9665932455002518, "precision@1": 0.928, "precision@5": 0.19760000000000003, "precision@10": 0.09980000000000001, "recall@1": 0.928, "recall@5": 0.988, "recall@10": 0.998, "f1@1": 0.928, "f1@5": 0.3293333333333333, "f1@10": 0.18145454545454545, "map@1": 0.928, "map@5": 0.9546500000000001, "map@10": 0.9561480158730159, "mrr@1": 0.928, "mrr@5": 0.9546500000000001, "mrr@10": 0.9561480158730159, "num_pred": 1000, "num_data": 1000 }, "SUN397": { "hit@1": 0.837, "hit@5": 0.975, "hit@10": 0.991, "ndcg_linear@1": 0.837, "ndcg_linear@5": 0.9163600193644518, "ndcg_linear@10": 0.921501619830454, "ndcg_exponential@1": 0.837, "ndcg_exponential@5": 0.9163600193644518, "ndcg_exponential@10": 0.921501619830454, "precision@1": 0.837, "precision@5": 0.195, "precision@10": 0.09910000000000001, "recall@1": 0.837, "recall@5": 0.975, "recall@10": 0.991, "f1@1": 0.837, "f1@5": 0.325, "f1@10": 0.18018181818181817, "map@1": 0.837, "map@5": 0.8963166666666668, "map@10": 0.8984174603174604, "mrr@1": 0.837, "mrr@5": 0.8963166666666668, "mrr@10": 0.8984174603174604, "num_pred": 1000, "num_data": 1000 }, "Place365": { "hit@1": 0.488, "hit@5": 0.754, "hit@10": 0.843, "ndcg_linear@1": 0.488, "ndcg_linear@5": 0.6315454829460373, "ndcg_linear@10": 0.6606594951524127, "ndcg_exponential@1": 0.488, "ndcg_exponential@5": 0.6315454829460373, "ndcg_exponential@10": 0.6606594951524127, "precision@1": 0.488, "precision@5": 0.15080000000000002, "precision@10": 0.0843, "recall@1": 0.488, "recall@5": 0.754, "recall@10": 0.843, "f1@1": 0.488, "f1@5": 0.25133333333333335, "f1@10": 0.15327272727272728, "map@1": 0.488, "map@5": 0.5905833333333332, "map@10": 0.6027853174603174, "mrr@1": 0.488, "mrr@5": 0.5905833333333332, "mrr@10": 0.6027853174603174, "num_pred": 1000, "num_data": 1000 }, "ImageNet-A": { "hit@1": 0.627, "hit@5": 0.845, "hit@10": 0.895, "ndcg_linear@1": 0.627, "ndcg_linear@5": 0.7471923630097598, "ndcg_linear@10": 0.7634058067891897, "ndcg_exponential@1": 0.627, "ndcg_exponential@5": 0.7471923630097598, "ndcg_exponential@10": 0.7634058067891897, "precision@1": 0.627, "precision@5": 0.169, "precision@10": 0.08950000000000001, "recall@1": 0.627, "recall@5": 0.845, "recall@10": 0.895, "f1@1": 0.627, "f1@5": 0.2816666666666667, "f1@10": 0.16272727272727272, "map@1": 0.627, "map@5": 0.7142333333333334, "map@10": 0.7209515873015874, "mrr@1": 0.627, "mrr@5": 0.7142333333333334, "mrr@10": 0.7209515873015874, "num_pred": 1000, "num_data": 1000 }, "ImageNet-R": { "hit@1": 0.912, "hit@5": 0.979, "hit@10": 0.988, "ndcg_linear@1": 0.912, "ndcg_linear@5": 0.951874082474405, "ndcg_linear@10": 0.9548219563052962, "ndcg_exponential@1": 0.912, "ndcg_exponential@5": 0.951874082474405, "ndcg_exponential@10": 0.9548219563052962, "precision@1": 0.912, "precision@5": 0.19580000000000003, "precision@10": 0.09880000000000003, "recall@1": 0.912, "recall@5": 0.979, "recall@10": 0.988, "f1@1": 0.912, "f1@5": 0.32633333333333336, "f1@10": 0.17963636363636362, "map@1": 0.912, "map@5": 0.9424833333333333, "map@10": 0.9437202380952381, "mrr@1": 0.912, "mrr@5": 0.9424833333333333, "mrr@10": 0.9437202380952381, "num_pred": 1000, "num_data": 1000 }, "ObjectNet": { "hit@1": 0.742, "hit@5": 0.906, "hit@10": 0.935, "ndcg_linear@1": 0.742, "ndcg_linear@5": 0.8319007951107223, "ndcg_linear@10": 0.8414834685011615, "ndcg_exponential@1": 0.742, "ndcg_exponential@5": 0.8319007951107223, "ndcg_exponential@10": 0.8414834685011615, "precision@1": 0.742, "precision@5": 0.18120000000000003, "precision@10": 0.0935, "recall@1": 0.742, "recall@5": 0.906, "recall@10": 0.935, "f1@1": 0.742, "f1@5": 0.302, "f1@10": 0.17, "map@1": 0.742, "map@5": 0.80705, "map@10": 0.8111309523809523, "mrr@1": 0.742, "mrr@5": 0.80705, "mrr@10": 0.8111309523809523, "num_pred": 1000, "num_data": 1000 }, "Country211": { "hit@1": 0.308, "hit@5": 0.535, "hit@10": 0.641, "ndcg_linear@1": 0.308, "ndcg_linear@5": 0.42778103855978467, "ndcg_linear@10": 0.46186570367981217, "ndcg_exponential@1": 0.308, "ndcg_exponential@5": 0.42778103855978467, "ndcg_exponential@10": 0.46186570367981217, "precision@1": 0.308, "precision@5": 0.107, "precision@10": 0.06409999999999999, "recall@1": 0.308, "recall@5": 0.535, "recall@10": 0.641, "f1@1": 0.308, "f1@5": 0.17833333333333337, "f1@10": 0.11654545454545456, "map@1": 0.308, "map@5": 0.3922, "map@10": 0.4061511904761904, "mrr@1": 0.308, "mrr@5": 0.3922, "mrr@10": 0.4061511904761904, "num_pred": 1000, "num_data": 1000 }, "OK-VQA": { "hit@1": 0.738, "hit@5": 0.927, "hit@10": 0.958, "ndcg_linear@1": 0.738, "ndcg_linear@5": 0.8437681382796158, "ndcg_linear@10": 0.8539481174803661, "ndcg_exponential@1": 0.738, "ndcg_exponential@5": 0.8437681382796158, "ndcg_exponential@10": 0.8539481174803661, "precision@1": 0.738, "precision@5": 0.1854, "precision@10": 0.09580000000000001, "recall@1": 0.738, "recall@5": 0.927, "recall@10": 0.958, "f1@1": 0.738, "f1@5": 0.30900000000000005, "f1@10": 0.1741818181818182, "map@1": 0.738, "map@5": 0.8155833333333333, "map@10": 0.8198753968253968, "mrr@1": 0.738, "mrr@5": 0.8155833333333333, "mrr@10": 0.8198753968253968, "num_pred": 1000, "num_data": 1000 }, "A-OKVQA": { "hit@1": 0.711, "hit@5": 0.941, "hit@10": 0.97, "ndcg_linear@1": 0.711, "ndcg_linear@5": 0.8418495966567268, "ndcg_linear@10": 0.8513793910680915, "ndcg_exponential@1": 0.711, "ndcg_exponential@5": 0.8418495966567268, "ndcg_exponential@10": 0.8513793910680915, "precision@1": 0.711, "precision@5": 0.1882, "precision@10": 0.09700000000000002, "recall@1": 0.711, "recall@5": 0.941, "recall@10": 0.97, "f1@1": 0.711, "f1@5": 0.31366666666666665, "f1@10": 0.17636363636363633, "map@1": 0.711, "map@5": 0.8081166666666667, "map@10": 0.8121333333333334, "mrr@1": 0.711, "mrr@5": 0.8081166666666667, "mrr@10": 0.8121333333333334, "num_pred": 1000, "num_data": 1000 }, "DocVQA": { "hit@1": 0.96, "hit@5": 0.993, "hit@10": 0.996, "ndcg_linear@1": 0.96, "ndcg_linear@5": 0.9797833092698106, "ndcg_linear@10": 0.9807883146670378, "ndcg_exponential@1": 0.96, "ndcg_exponential@5": 0.9797833092698106, "ndcg_exponential@10": 0.9807883146670378, "precision@1": 0.96, "precision@5": 0.19860000000000003, "precision@10": 0.09960000000000002, "recall@1": 0.96, "recall@5": 0.993, "recall@10": 0.996, "f1@1": 0.96, "f1@5": 0.331, "f1@10": 0.18109090909090905, "map@1": 0.96, "map@5": 0.9752, "map@10": 0.9756345238095239, "mrr@1": 0.96, "mrr@5": 0.9752, "mrr@10": 0.9756345238095239, "num_pred": 1000, "num_data": 1000 }, "InfographicsVQA": { "hit@1": 0.74, "hit@5": 0.887, "hit@10": 0.925, "ndcg_linear@1": 0.74, "ndcg_linear@5": 0.8215002632703688, "ndcg_linear@10": 0.8338866735706076, "ndcg_exponential@1": 0.74, "ndcg_exponential@5": 0.8215002632703688, "ndcg_exponential@10": 0.8338866735706076, "precision@1": 0.74, "precision@5": 0.17740000000000003, "precision@10": 0.09250000000000001, "recall@1": 0.74, "recall@5": 0.887, "recall@10": 0.925, "f1@1": 0.74, "f1@5": 0.2956666666666667, "f1@10": 0.16818181818181815, "map@1": 0.74, "map@5": 0.7993833333333334, "map@10": 0.8045535714285714, "mrr@1": 0.74, "mrr@5": 0.7993833333333334, "mrr@10": 0.8045535714285714, "num_pred": 1000, "num_data": 1000 }, "ChartQA": { "hit@1": 0.681, "hit@5": 0.826, "hit@10": 0.872, "ndcg_linear@1": 0.681, "ndcg_linear@5": 0.7580943344500665, "ndcg_linear@10": 0.7729516370160638, "ndcg_exponential@1": 0.681, "ndcg_exponential@5": 0.7580943344500665, "ndcg_exponential@10": 0.7729516370160638, "precision@1": 0.681, "precision@5": 0.16519999999999999, "precision@10": 0.08720000000000001, "recall@1": 0.681, "recall@5": 0.826, "recall@10": 0.872, "f1@1": 0.681, "f1@5": 0.2753333333333334, "f1@10": 0.15854545454545454, "map@1": 0.681, "map@5": 0.7355166666666666, "map@10": 0.7416400793650794, "mrr@1": 0.681, "mrr@5": 0.7355166666666666, "mrr@10": 0.7416400793650794, "num_pred": 1000, "num_data": 1000 }, "Visual7W": { "hit@1": 0.653, "hit@5": 0.911, "hit@10": 0.965, "ndcg_linear@1": 0.653, "ndcg_linear@5": 0.7957439829395048, "ndcg_linear@10": 0.8132923052264777, "ndcg_exponential@1": 0.653, "ndcg_exponential@5": 0.7957439829395048, "ndcg_exponential@10": 0.8132923052264777, "precision@1": 0.653, "precision@5": 0.18220000000000003, "precision@10": 0.09650000000000002, "recall@1": 0.653, "recall@5": 0.911, "recall@10": 0.965, "f1@1": 0.653, "f1@5": 0.3036666666666667, "f1@10": 0.17545454545454545, "map@1": 0.653, "map@5": 0.75685, "map@10": 0.7641448412698413, "mrr@1": 0.653, "mrr@5": 0.75685, "mrr@10": 0.7641448412698413, "num_pred": 1000, "num_data": 1000 }, "ScienceQA": { "hit@1": 0.627, "hit@5": 0.838, "hit@10": 0.898, "ndcg_linear@1": 0.627, "ndcg_linear@5": 0.7441307828226104, "ndcg_linear@10": 0.7641257526069815, "ndcg_exponential@1": 0.627, "ndcg_exponential@5": 0.7441307828226104, "ndcg_exponential@10": 0.7641257526069815, "precision@1": 0.627, "precision@5": 0.16760000000000003, "precision@10": 0.0898, "recall@1": 0.627, "recall@5": 0.838, "recall@10": 0.898, "f1@1": 0.627, "f1@5": 0.2793333333333334, "f1@10": 0.16327272727272726, "map@1": 0.627, "map@5": 0.7125, "map@10": 0.7211003968253967, "mrr@1": 0.627, "mrr@5": 0.7125, "mrr@10": 0.7211003968253967, "num_pred": 1000, "num_data": 1000 }, "VizWiz": { "hit@1": 0.569, "hit@5": 0.724, "hit@10": 0.761, "ndcg_linear@1": 0.569, "ndcg_linear@5": 0.6555370943694709, "ndcg_linear@10": 0.6678951249768675, "ndcg_exponential@1": 0.569, "ndcg_exponential@5": 0.6555370943694709, "ndcg_exponential@10": 0.6678951249768675, "precision@1": 0.569, "precision@5": 0.1448, "precision@10": 0.0761, "recall@1": 0.569, "recall@5": 0.724, "recall@10": 0.761, "f1@1": 0.569, "f1@5": 0.24133333333333337, "f1@10": 0.13836363636363638, "map@1": 0.569, "map@5": 0.6323666666666666, "map@10": 0.6377007936507937, "mrr@1": 0.569, "mrr@5": 0.6323666666666666, "mrr@10": 0.6377007936507937, "num_pred": 1000, "num_data": 1000 }, "GQA": { "hit@1": 0.624, "hit@5": 0.823, "hit@10": 0.886, "ndcg_linear@1": 0.624, "ndcg_linear@5": 0.7342658154287309, "ndcg_linear@10": 0.7548121833408118, "ndcg_exponential@1": 0.624, "ndcg_exponential@5": 0.7342658154287309, "ndcg_exponential@10": 0.7548121833408118, "precision@1": 0.624, "precision@5": 0.16460000000000002, "precision@10": 0.08860000000000001, "recall@1": 0.624, "recall@5": 0.823, "recall@10": 0.886, "f1@1": 0.624, "f1@5": 0.2743333333333334, "f1@10": 0.1610909090909091, "map@1": 0.624, "map@5": 0.7043833333333333, "map@10": 0.7129646825396826, "mrr@1": 0.624, "mrr@5": 0.7043833333333333, "mrr@10": 0.7129646825396826, "num_pred": 1000, "num_data": 1000 }, "TextVQA": { "hit@1": 0.882, "hit@5": 0.937, "hit@10": 0.948, "ndcg_linear@1": 0.882, "ndcg_linear@5": 0.9118377392749808, "ndcg_linear@10": 0.9152642970600482, "ndcg_exponential@1": 0.882, "ndcg_exponential@5": 0.9118377392749808, "ndcg_exponential@10": 0.9152642970600482, "precision@1": 0.882, "precision@5": 0.18740000000000004, "precision@10": 0.09480000000000001, "recall@1": 0.882, "recall@5": 0.937, "recall@10": 0.948, "f1@1": 0.882, "f1@5": 0.31233333333333335, "f1@10": 0.17236363636363636, "map@1": 0.882, "map@5": 0.9034166666666668, "map@10": 0.9047551587301588, "mrr@1": 0.882, "mrr@5": 0.9034166666666668, "mrr@10": 0.9047551587301588, "num_pred": 1000, "num_data": 1000 }, "VisDial": { "hit@1": 0.855, "hit@5": 0.974, "hit@10": 0.991, "ndcg_linear@1": 0.855, "ndcg_linear@5": 0.9218847416528654, "ndcg_linear@10": 0.9274132808218436, "ndcg_exponential@1": 0.855, "ndcg_exponential@5": 0.9218847416528654, "ndcg_exponential@10": 0.9274132808218436, "precision@1": 0.855, "precision@5": 0.1948, "precision@10": 0.09910000000000002, "recall@1": 0.855, "recall@5": 0.974, "recall@10": 0.991, "f1@1": 0.855, "f1@5": 0.3246666666666666, "f1@10": 0.18018181818181817, "map@1": 0.855, "map@5": 0.9042, "map@10": 0.9064972222222223, "mrr@1": 0.855, "mrr@5": 0.9042, "mrr@10": 0.9064972222222223, "num_pred": 1000, "num_data": 1000 }, "CIRR": { "hit@1": 0.695, "hit@5": 0.936, "hit@10": 0.97, "ndcg_linear@1": 0.695, "ndcg_linear@5": 0.8303720235690268, "ndcg_linear@10": 0.8416097816203485, "ndcg_exponential@1": 0.695, "ndcg_exponential@5": 0.8303720235690268, "ndcg_exponential@10": 0.8416097816203485, "precision@1": 0.695, "precision@5": 0.1872, "precision@10": 0.09700000000000002, "recall@1": 0.695, "recall@5": 0.936, "recall@10": 0.97, "f1@1": 0.695, "f1@5": 0.312, "f1@10": 0.17636363636363636, "map@1": 0.695, "map@5": 0.7945166666666666, "map@10": 0.7992964285714286, "mrr@1": 0.695, "mrr@5": 0.7945166666666666, "mrr@10": 0.7992964285714286, "num_pred": 1000, "num_data": 1000 }, "VisualNews_t2i": { "hit@1": 0.805, "hit@5": 0.919, "hit@10": 0.941, "ndcg_linear@1": 0.805, "ndcg_linear@5": 0.867631837778723, "ndcg_linear@10": 0.8750135606412587, "ndcg_exponential@1": 0.805, "ndcg_exponential@5": 0.867631837778723, "ndcg_exponential@10": 0.8750135606412587, "precision@1": 0.805, "precision@5": 0.18380000000000002, "precision@10": 0.0941, "recall@1": 0.805, "recall@5": 0.919, "recall@10": 0.941, "f1@1": 0.805, "f1@5": 0.30633333333333335, "f1@10": 0.17109090909090907, "map@1": 0.805, "map@5": 0.8504, "map@10": 0.8536031746031746, "mrr@1": 0.805, "mrr@5": 0.8504, "mrr@10": 0.8536031746031746, "num_pred": 1000, "num_data": 1000 }, "VisualNews_i2t": { "hit@1": 0.839, "hit@5": 0.944, "hit@10": 0.96, "ndcg_linear@1": 0.839, "ndcg_linear@5": 0.8971916372890704, "ndcg_linear@10": 0.9024827626264819, "ndcg_exponential@1": 0.839, "ndcg_exponential@5": 0.8971916372890704, "ndcg_exponential@10": 0.9024827626264819, "precision@1": 0.839, "precision@5": 0.18880000000000002, "precision@10": 0.09600000000000002, "recall@1": 0.839, "recall@5": 0.944, "recall@10": 0.96, "f1@1": 0.839, "f1@5": 0.3146666666666667, "f1@10": 0.17454545454545456, "map@1": 0.839, "map@5": 0.8814333333333333, "map@10": 0.8836849206349207, "mrr@1": 0.839, "mrr@5": 0.8814333333333333, "mrr@10": 0.8836849206349207, "num_pred": 1000, "num_data": 1000 }, "MSCOCO_t2i": { "hit@1": 0.826, "hit@5": 0.975, "hit@10": 0.989, "ndcg_linear@1": 0.826, "ndcg_linear@5": 0.9096247418711488, "ndcg_linear@10": 0.9142456743452003, "ndcg_exponential@1": 0.826, "ndcg_exponential@5": 0.9096247418711488, "ndcg_exponential@10": 0.9142456743452003, "precision@1": 0.826, "precision@5": 0.19500000000000006, "precision@10": 0.0989, "recall@1": 0.826, "recall@5": 0.975, "recall@10": 0.989, "f1@1": 0.826, "f1@5": 0.325, "f1@10": 0.17981818181818182, "map@1": 0.826, "map@5": 0.8874666666666667, "map@10": 0.8894313492063491, "mrr@1": 0.826, "mrr@5": 0.8874666666666667, "mrr@10": 0.8894313492063491, "num_pred": 1000, "num_data": 1000 }, "MSCOCO_i2t": { "hit@1": 0.801, "hit@5": 0.962, "hit@10": 0.987, "ndcg_linear@1": 0.801, "ndcg_linear@5": 0.8895554177540842, "ndcg_linear@10": 0.8978197338403454, "ndcg_exponential@1": 0.801, "ndcg_exponential@5": 0.8895554177540842, "ndcg_exponential@10": 0.8978197338403454, "precision@1": 0.801, "precision@5": 0.19240000000000004, "precision@10": 0.09870000000000002, "recall@1": 0.801, "recall@5": 0.962, "recall@10": 0.987, "f1@1": 0.801, "f1@5": 0.3206666666666667, "f1@10": 0.17945454545454545, "map@1": 0.801, "map@5": 0.8652000000000001, "map@10": 0.8687182539682539, "mrr@1": 0.801, "mrr@5": 0.8652000000000001, "mrr@10": 0.8687182539682539, "num_pred": 1000, "num_data": 1000 }, "NIGHTS": { "hit@1": 0.67, "hit@5": 0.98, "hit@10": 0.994, "ndcg_linear@1": 0.67, "ndcg_linear@5": 0.8514951168442588, "ndcg_linear@10": 0.8562767340903585, "ndcg_exponential@1": 0.67, "ndcg_exponential@5": 0.8514951168442588, "ndcg_exponential@10": 0.8562767340903585, "precision@1": 0.67, "precision@5": 0.19600000000000004, "precision@10": 0.09940000000000002, "recall@1": 0.67, "recall@5": 0.98, "recall@10": 0.994, "f1@1": 0.67, "f1@5": 0.3266666666666666, "f1@10": 0.18072727272727268, "map@1": 0.67, "map@5": 0.8072333333333334, "map@10": 0.8093563492063491, "mrr@1": 0.67, "mrr@5": 0.8072333333333334, "mrr@10": 0.8093563492063491, "num_pred": 1000, "num_data": 1000 }, "WebQA": { "hit@1": 0.927, "hit@5": 0.99, "hit@10": 0.996, "ndcg_linear@1": 0.927, "ndcg_linear@5": 0.9646122229672621, "ndcg_linear@10": 0.9665993599079417, "ndcg_exponential@1": 0.927, "ndcg_exponential@5": 0.9646122229672621, "ndcg_exponential@10": 0.9665993599079417, "precision@1": 0.927, "precision@5": 0.19800000000000004, "precision@10": 0.09960000000000002, "recall@1": 0.927, "recall@5": 0.99, "recall@10": 0.996, "f1@1": 0.927, "f1@5": 0.33, "f1@10": 0.18109090909090905, "map@1": 0.927, "map@5": 0.9558166666666666, "map@10": 0.9566619047619047, "mrr@1": 0.927, "mrr@5": 0.9558166666666666, "mrr@10": 0.9566619047619047, "num_pred": 1000, "num_data": 1000 }, "FashionIQ": { "hit@1": 0.322, "hit@5": 0.595, "hit@10": 0.704, "ndcg_linear@1": 0.322, "ndcg_linear@5": 0.46773316488052585, "ndcg_linear@10": 0.5034661018908781, "ndcg_exponential@1": 0.322, "ndcg_exponential@5": 0.46773316488052585, "ndcg_exponential@10": 0.5034661018908781, "precision@1": 0.322, "precision@5": 0.119, "precision@10": 0.0704, "recall@1": 0.322, "recall@5": 0.595, "recall@10": 0.704, "f1@1": 0.322, "f1@5": 0.1983333333333334, "f1@10": 0.128, "map@1": 0.322, "map@5": 0.42531666666666673, "map@10": 0.44034761904761904, "mrr@1": 0.322, "mrr@5": 0.42531666666666673, "mrr@10": 0.44034761904761904, "num_pred": 1000, "num_data": 1000 }, "Wiki-SS-NQ": { "hit@1": 0.742, "hit@5": 0.913, "hit@10": 0.948, "ndcg_linear@1": 0.742, "ndcg_linear@5": 0.8368546498592745, "ndcg_linear@10": 0.8483141717811807, "ndcg_exponential@1": 0.742, "ndcg_exponential@5": 0.8368546498592745, "ndcg_exponential@10": 0.8483141717811807, "precision@1": 0.742, "precision@5": 0.1826, "precision@10": 0.09480000000000001, "recall@1": 0.742, "recall@5": 0.913, "recall@10": 0.948, "f1@1": 0.742, "f1@5": 0.3043333333333333, "f1@10": 0.17236363636363636, "map@1": 0.742, "map@5": 0.8111666666666666, "map@10": 0.8159821428571429, "mrr@1": 0.742, "mrr@5": 0.8111666666666666, "mrr@10": 0.8159821428571429, "num_pred": 1000, "num_data": 1000 }, "OVEN": { "hit@1": 0.725, "hit@5": 0.904, "hit@10": 0.943, "ndcg_linear@1": 0.725, "ndcg_linear@5": 0.8239706868512274, "ndcg_linear@10": 0.8365741461671187, "ndcg_exponential@1": 0.725, "ndcg_exponential@5": 0.8239706868512274, "ndcg_exponential@10": 0.8365741461671187, "precision@1": 0.725, "precision@5": 0.18080000000000002, "precision@10": 0.09430000000000001, "recall@1": 0.725, "recall@5": 0.904, "recall@10": 0.943, "f1@1": 0.725, "f1@5": 0.3013333333333334, "f1@10": 0.17145454545454544, "map@1": 0.725, "map@5": 0.7969833333333334, "map@10": 0.802181746031746, "mrr@1": 0.725, "mrr@5": 0.7969833333333334, "mrr@10": 0.802181746031746, "num_pred": 1000, "num_data": 1000 }, "EDIS": { "hit@1": 0.914, "hit@5": 0.988, "hit@10": 0.996, "ndcg_linear@1": 0.914, "ndcg_linear@5": 0.957026923765827, "ndcg_linear@10": 0.9597672173910449, "ndcg_exponential@1": 0.914, "ndcg_exponential@5": 0.957026923765827, "ndcg_exponential@10": 0.9597672173910449, "precision@1": 0.914, "precision@5": 0.19760000000000003, "precision@10": 0.09960000000000001, "recall@1": 0.914, "recall@5": 0.988, "recall@10": 0.996, "f1@1": 0.914, "f1@5": 0.32933333333333337, "f1@10": 0.18109090909090905, "map@1": 0.914, "map@5": 0.9464166666666668, "map@10": 0.9476369047619047, "mrr@1": 0.914, "mrr@5": 0.9464166666666668, "mrr@10": 0.9476369047619047, "num_pred": 1000, "num_data": 1000 }, "MSCOCO": { "hit@1": 0.815, "hit@5": 0.941, "hit@10": 0.962, "ndcg_linear@1": 0.815, "ndcg_linear@5": 0.8851674296999685, "ndcg_linear@10": 0.8921377681839521, "ndcg_exponential@1": 0.815, "ndcg_exponential@5": 0.8851674296999685, "ndcg_exponential@10": 0.8921377681839521, "precision@1": 0.815, "precision@5": 0.18820000000000003, "precision@10": 0.09620000000000002, "recall@1": 0.815, "recall@5": 0.941, "recall@10": 0.962, "f1@1": 0.815, "f1@5": 0.31366666666666665, "f1@10": 0.1749090909090909, "map@1": 0.815, "map@5": 0.8663333333333333, "map@10": 0.8693142857142857, "mrr@1": 0.815, "mrr@5": 0.8663333333333333, "mrr@10": 0.8693142857142857, "num_pred": 1000, "num_data": 1000 }, "RefCOCO": { "hit@1": 0.935, "hit@5": 0.997, "hit@10": 0.999, "ndcg_linear@1": 0.935, "ndcg_linear@5": 0.9724617299760828, "ndcg_linear@10": 0.9730841281357341, "ndcg_exponential@1": 0.935, "ndcg_exponential@5": 0.9724617299760828, "ndcg_exponential@10": 0.9730841281357341, "precision@1": 0.935, "precision@5": 0.19940000000000002, "precision@10": 0.0999, "recall@1": 0.935, "recall@5": 0.997, "recall@10": 0.999, "f1@1": 0.935, "f1@5": 0.33233333333333337, "f1@10": 0.18163636363636362, "map@1": 0.935, "map@5": 0.9639166666666668, "map@10": 0.9641595238095239, "mrr@1": 0.935, "mrr@5": 0.9639166666666668, "mrr@10": 0.9641595238095239, "num_pred": 1000, "num_data": 1000 }, "RefCOCO-Matching": { "hit@1": 0.929, "hit@5": 1.0, "hit@10": 1.0, "ndcg_linear@1": 0.929, "ndcg_linear@5": 0.9732900760500937, "ndcg_linear@10": 0.9732900760500937, "ndcg_exponential@1": 0.929, "ndcg_exponential@5": 0.9732900760500937, "ndcg_exponential@10": 0.9732900760500937, "precision@1": 0.929, "precision@5": 0.20000000000000004, "precision@10": 0.10000000000000002, "recall@1": 0.929, "recall@5": 1.0, "recall@10": 1.0, "f1@1": 0.929, "f1@5": 0.3333333333333333, "f1@10": 0.18181818181818182, "map@1": 0.929, "map@5": 0.9638666666666666, "map@10": 0.9638666666666666, "mrr@1": 0.929, "mrr@5": 0.9638666666666666, "mrr@10": 0.9638666666666666, "num_pred": 1000, "num_data": 1000 }, "Visual7W-Pointing": { "hit@1": 0.818, "hit@5": 0.942, "hit@10": 0.964, "ndcg_linear@1": 0.818, "ndcg_linear@5": 0.8865860771711156, "ndcg_linear@10": 0.8936311903397262, "ndcg_exponential@1": 0.818, "ndcg_exponential@5": 0.8865860771711156, "ndcg_exponential@10": 0.8936311903397262, "precision@1": 0.818, "precision@5": 0.18840000000000004, "precision@10": 0.09640000000000001, "recall@1": 0.818, "recall@5": 0.942, "recall@10": 0.964, "f1@1": 0.818, "f1@5": 0.314, "f1@10": 0.17527272727272725, "map@1": 0.818, "map@5": 0.8679000000000001, "map@10": 0.8707690476190477, "mrr@1": 0.818, "mrr@5": 0.8679000000000001, "mrr@10": 0.8707690476190477, "num_pred": 1000, "num_data": 1000 } }, "visdoc": { "ViDoRe_arxivqa": "DIR_N/A", "ViDoRe_docvqa": "DIR_N/A", "ViDoRe_infovqa": "DIR_N/A", "ViDoRe_tabfquad": "DIR_N/A", "ViDoRe_tatdqa": "DIR_N/A", "ViDoRe_shiftproject": "DIR_N/A", "ViDoRe_syntheticDocQA_artificial_intelligence": "DIR_N/A", "ViDoRe_syntheticDocQA_energy": "DIR_N/A", "ViDoRe_syntheticDocQA_government_reports": "DIR_N/A", "ViDoRe_syntheticDocQA_healthcare_industry": "DIR_N/A", "ViDoRe_esg_reports_human_labeled_v2": "DIR_N/A", "ViDoRe_biomedical_lectures_v2": "DIR_N/A", "ViDoRe_biomedical_lectures_v2_multilingual": "DIR_N/A", "ViDoRe_economics_reports_v2": "DIR_N/A", "ViDoRe_economics_reports_v2_multilingual": "DIR_N/A", "ViDoRe_esg_reports_v2": "DIR_N/A", "ViDoRe_esg_reports_v2_multilingual": "DIR_N/A", "VisRAG_ArxivQA": "DIR_N/A", "VisRAG_ChartQA": "DIR_N/A", "VisRAG_MP-DocVQA": "DIR_N/A", "VisRAG_SlideVQA": "DIR_N/A", "VisRAG_InfoVQA": "DIR_N/A", "VisRAG_PlotQA": "DIR_N/A", "ViDoSeek-page": "DIR_N/A", "ViDoSeek-doc": "DIR_N/A", "MMLongBench-page": "DIR_N/A", "MMLongBench-doc": "DIR_N/A" }, "video": { "DiDeMo": "DIR_N/A", "MSR-VTT": "DIR_N/A", "MSVD": "DIR_N/A", "VATEX": "DIR_N/A", "YouCook2": "DIR_N/A", "QVHighlight": "DIR_N/A", "Charades-STA": "DIR_N/A", "MomentSeeker": "DIR_N/A", "K700": "DIR_N/A", "SmthSmthV2": "DIR_N/A", "HMDB51": "DIR_N/A", "UCF101": "DIR_N/A", "Breakfast": "DIR_N/A", "MVBench": "DIR_N/A", "Video-MME": "DIR_N/A", "NExTQA": "DIR_N/A", "EgoSchema": "DIR_N/A", "ActivityNetQA": "DIR_N/A" } } }